Search Results for author: Xi Chen

Found 192 papers, 47 papers with code

Building Goal-oriented Document-grounded Dialogue Systems

no code implementations ACL (dialdoc) 2021 Xi Chen, Faner Lin, Yeju Zhou, Kaixin Ma, Jonathan Francis, Eric Nyberg, Alessandro Oltramari

In this paper, we describe our systems for solving the two Doc2Dial shared task: knowledge identification and response generation.

Data Augmentation

A Three-step Method for Multi-Hop Inference Explanation Regeneration

no code implementations NAACL (TextGraphs) 2021 Yuejia Xiang, Yunyan Zhang, Xiaoming Shi, Bo Liu, Wandi Xu, Xi Chen

Then, a selection module is employed to choose those most relative facts in an autoregressive manner, giving a preliminary order for the retrieved facts.

Re-Ranking

Collaborative learning of images and geometrics for predicting isocitrate dehydrogenase status of glioma

no code implementations14 Jan 2022 Yiran Wei, Chao Li, Xi Chen, Carola-Bibiane Schönlieb, Stephen J. Price

Further, the collaborative learning model achieves better performance than either the CNN or the GNN alone.

Generalized DataWeighting via Class-Level Gradient Manipulation

1 code implementation NeurIPS 2021 Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue (Steve) Liu, Hao liu, Dejing Dou

To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.

Leveraging Intrinsic Gradient Information for Further Training of Differentiable Machine Learning Models

no code implementations30 Nov 2021 Chris McDonagh, Xi Chen

Designing models that produce accurate predictions is the fundamental objective of machine learning (ML).

Interval-valued q-Rung Orthopair Fuzzy Choquet Integral Operators and Its Application in Group Decision Making

no code implementations30 Nov 2021 Benting Wan, Juelin Huang, Xi Chen

It is more flexible for decision makers to evaluate by interval-valued q-rung orthopair fuzzy set (IVq-ROFS), which offers fuzzy decision-making more applicational space.

Decision Making

Fairness-aware Online Price Discrimination with Nonparametric Demand Models

no code implementations16 Nov 2021 Xi Chen, Xuan Zhang, Yuan Zhou

To handle this general class, we propose a soft fairness constraint and develop the dynamic pricing policy that achieves $\tilde{O}(T^{4/5})$ regret.

Fairness

On the Complexity of Dynamic Submodular Maximization

no code implementations5 Nov 2021 Xi Chen, Binghui Peng

We study dynamic algorithms for the problem of maximizing a monotone submodular function over a stream of $n$ insertions and deletions.

Generalized Data Weighting via Class-level Gradient Manipulation

1 code implementation29 Oct 2021 Can Chen, Shuhao Zheng, Xi Chen, Erqun Dong, Xue Liu, Hao liu, Dejing Dou

To be specific, GDW unrolls the loss gradient to class-level gradients by the chain rule and reweights the flow of each gradient separately.

Brain-inspired feature exaggeration in generative replay for continual learning

no code implementations26 Oct 2021 Jack Millichamp, Xi Chen

The catastrophic forgetting of previously learnt classes is one of the main obstacles to the successful development of a reliable and accurate generative continual learning model.

class-incremental learning Incremental Learning

PAC-Bayes Information Bottleneck

1 code implementation29 Sep 2021 Zifeng Wang, Shao-Lun Huang, Ercan E. Kuruoglu, Jimeng Sun, Xi Chen, Yefeng Zheng

In this work, we build a new IB based on the trade-off between the accuracy and complexity of learned weights of NNs.

Deep Learning based Model-free Robust Load Restoration to Enhance Bulk System Resilience with Wind Power Penetration

no code implementations16 Sep 2021 Jin Zhao, Fangxing Li, Xi Chen, Qiuwei Wu

This paper proposes a new deep learning (DL) based model-free robust method for bulk system on-line load restoration with high penetration of wind power.

Differential Privacy in Personalized Pricing with Nonparametric Demand Models

no code implementations10 Sep 2021 Xi Chen, Sentao Miao, Yining Wang

In the recent decades, the advance of information technology and abundant personal data facilitate the application of algorithmic personalized pricing.

Adversarial Attack

Risk-Adjusted Valuation for Real Option Decisions

no code implementations10 Sep 2021 Carol Alexander, Xi Chen, Charles Ward

We propose a risk-adjusted valuation model to facilitate investors' subjective decision making, in response to the market valuation of an investment opportunity.

Decision Making

Graph-MVP: Multi-View Prototypical Contrastive Learning for Multiplex Graphs

no code implementations8 Sep 2021 Baoyu Jing, Yuejia Xiang, Xi Chen, Yu Chen, Hanghang Tong

To address these challenges, we propose a novel Graph Multi-View Prototypical (Graph-MVP) framework to extract node embeddings on multiplex graphs.

Contrastive Learning Graph Representation Learning +1

Adaptive unsupervised learning with enhanced feature representation for intra-tumor partitioning and survival prediction for glioblastoma

no code implementations21 Aug 2021 YiFan Li, Chao Li, Yiran Wei, Stephen Price, Carola-Bibiane Schönlieb, Xi Chen

In this paper, we propose an adaptive unsupervised learning approach for efficient MRI intra-tumor partitioning and glioblastoma survival prediction.

Survival Prediction

CONNER: A Cascade Count and Measurement Extraction Tool for Scientific Discourse

no code implementations SEMEVAL 2021 Jiarun Cao, Yuejia Xiang, Yunyan Zhang, Zhiyuan Qi, Xi Chen, Yefeng Zheng

Accordingly, we propose CONNER, a cascade count and measurement extraction tool that can identify entities and the corresponding relations in a two-step pipeline model.

Joint Entity and Relation Extraction

Pruning Ternary Quantization

no code implementations23 Jul 2021 Dan Liu, Xi Chen, Jie Fu, Xue Liu

We propose pruning ternary quantization (PTQ), a simple, yet effective, symmetric ternary quantization method.

Quantization

Adversarial Robustness of Probabilistic Network Embedding for Link Prediction

no code implementations5 Jul 2021 Xi Chen, Bo Kang, Jefrey Lijffijt, Tijl De Bie

However, these methods lack transparency when compared to simpler baselines, and as a result their robustness against adversarial attacks is a possible point of concern: could one or a few small adversarial modifications to the network have a large impact on the link prediction performance when using a network embedding model?

Adversarial Robustness Link Prediction +1

PRASEMap: A Probabilistic Reasoning and Semantic Embedding based Knowledge Graph Alignment System

1 code implementation16 Jun 2021 Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yefeng Zheng

Knowledge Graph (KG) alignment aims at finding equivalent entities and relations (i. e., mappings) between two KGs.

Field Embedding: A Unified Grain-Based Framework for Word Representation

no code implementations NAACL 2021 Junjie Luo, Xi Chen, Jichao Sun, Yuejia Xiang, Ningyu Zhang, Xiang Wan

Word representations empowered with additional linguistic information have been widely studied and proved to outperform traditional embeddings.

Word Embeddings

Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning

no code implementations NeurIPS 2021 Nan Ding, Xi Chen, Tomer Levinboim, Sebastian Goodman, Radu Soricut

Despite recent advances in its theoretical understanding, there still remains a significant gap in the ability of existing PAC-Bayesian theories on meta-learning to explain performance improvements in the few-shot learning setting, where the number of training examples in the target tasks is severely limited.

Few-Shot Learning

Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding

1 code implementation12 May 2021 Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, Yefeng Zheng

Knowledge Graph (KG) alignment is to discover the mappings (i. e., equivalent entities, relations, and others) between two KGs.

Interventional Aspect-Based Sentiment Analysis

no code implementations20 Apr 2021 Zhen Bi, Ningyu Zhang, Ganqiang Ye, Haiyang Yu, Xi Chen, Huajun Chen

Recent neural-based aspect-based sentiment analysis approaches, though achieving promising improvement on benchmark datasets, have reported suffering from poor robustness when encountering confounder such as non-target aspects.

Aspect-Based Sentiment Analysis

Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management

1 code implementation NAACL 2021 Zhengxu Hou, Bang Liu, Ruihui Zhao, Zijing Ou, Yafei Liu, Xi Chen, Yefeng Zheng

For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs.

FEW-SHOTLEARNING WITH WEAK SUPERVISION

no code implementations ICLR Workshop Learning_to_Learn 2021 Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic

Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.

Meta-Learning Variational Inference

BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification

no code implementations10 Mar 2021 Chao Li, Yiran Wei, Xi Chen, Carola-Bibiane Schonlieb

The proposed BrainNetGAN is a generative adversarial network variant to augment the brain structural connectivity matrices for binary dementia classification tasks.

Data Augmentation General Classification

No Discounted-Regret Learning in Adversarial Bandits with Delays

no code implementations8 Mar 2021 Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet

Using these bounds, we show that EXP3 and FKM have no discounted-regret even for $d_{t}=O\left(t\log t\right)$.

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

no code implementations5 Mar 2021 Ali Ghadirzadeh, Xi Chen, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic

Our results show that the proposed method can successfully adapt a trained policy to different robotic platforms with novel physical parameters and the superiority of our meta-learning algorithm compared to state-of-the-art methods for the introduced few-shot policy adaptation problem.

Meta-Learning

Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference

no code implementations4 Mar 2021 Jiyuan Tu, Weidong Liu, Xiaojun Mao, Xi Chen

Based on the proposed VRMOM estimator, we develop a general distributed inference algorithm that is robust against Byzantine failures.

Lifelong Learning based Disease Diagnosis on Clinical Notes

1 code implementation27 Feb 2021 Zifeng Wang, Yifan Yang, Rui Wen, Xi Chen, Shao-Lun Huang, Yefeng Zheng

Current deep learning based disease diagnosis systems usually fall short in catastrophic forgetting, i. e., directly fine-tuning the disease diagnosis model on new tasks usually leads to abrupt decay of performance on previous tasks.

Learning a Product Relevance Model from Click-Through Data in E-Commerce

no code implementations14 Feb 2021 Shaowei Yao, Jiwei Tan, Xi Chen, Keping Yang, Rong Xiao, Hongbo Deng, Xiaojun Wan

We propose a novel way to consider samples of different relevance confidence, and come up with a new training objective to learn a robust relevance model with desirable score distribution.

Click-Through Rate Prediction

Does Probabilistic Constellation Shaping Benefit IM-DD Systems without Optical Amplifiers?

no code implementations9 Feb 2021 Di Che, Junho Cho, Xi Chen

Probabilistic constellation shaping (PCS) has been widely applied to amplified coherent optical transmissions owing to its shaping gain over the uniform signaling and fine-grained rate adaptation to the underlying fiber channel condition.

Online Statistical Inference for Stochastic Optimization via Kiefer-Wolfowitz Methods

no code implementations5 Feb 2021 Xi Chen, Zehua Lai, He Li, Yichen Zhang

We first present the asymptotic distribution for the Polyak-Ruppert-averaging type Kiefer-Wolfowitz (AKW) estimators, whose asymptotic covariance matrices depend on the function-value query complexity and the distribution of search directions.

Stochastic Optimization

Monitoring SEIRD model parameters using MEWMA for the COVID-19 pandemic with application to the State of Qatar

no code implementations29 Jan 2021 Edward L. Boone, Abdel-Salam G. Abdel-Salam, Indranil Sahoo, Ryad Ghanam, Xi Chen, Aiman Hanif

During the current COVID-19 pandemic, decision makers are tasked with implementing and evaluating strategies for both treatment and disease prevention.

Methodology Applications

Experimental implementation of precisely tailored light-matter interaction via inverse engineering

no code implementations29 Jan 2021 Ying Yan, Chunyan Shi, Adam Kinos, Hafsa Syed, Sebastian Horvath, Andreas Walther, Lars Rippe, Xi Chen, Stefan Kröll

Here, we implement fast and robust control for the state preparation and state engineering in a rare-earth ions system.

Quantum Physics

Denoising Single Voxel Magnetic Resonance Spectroscopy with Deep Learning on Repeatedly Sampled In Vivo Data

no code implementations26 Jan 2021 Wanqi Hu, Dicheng Chen, Tianyu Qiu, Hao Chen, Xi Chen, Lin Yang, Gen Yan, Di Guo, Xiaobo Qu

Methods: By exploring the multiple sampled data, a deep learning denoising approach is proposed to learn a mapping from the low SNR signal to the high SNR one.

Denoising

Adversarial Combinatorial Bandits with General Non-linear Reward Functions

no code implementations5 Jan 2021 Xi Chen, Yanjun Han, Yining Wang

{The adversarial combinatorial bandit with general non-linear reward is an important open problem in bandit literature, and it is still unclear whether there is a significant gap from the case of linear reward, stochastic bandit, or semi-bandit feedback.}

Conditional Diffusion for Interactive Segmentation

no code implementations ICCV 2021 Xi Chen, Zhiyan Zhao, Feiwu Yu, Yilei Zhang, Manni Duan

In click-based interactive segmentation, the mask extraction process is dictated by positive/negative user clicks; however, most existing methods do not fully exploit the user cues, requiring excessive numbers of clicks for satisfactory results.

Interactive Segmentation

KETG: A Knowledge Enhanced Text Generation Framework

no code implementations1 Jan 2021 Yan Cui, Xi Chen, Jiang Qian, Bojin Zhuang, Shaojun Wang, Jing Xiao

Embedding logical knowledge information into text generation is a challenging NLP task.

Text Generation

Full C-Band WDM Transmission of Nonlinearity-Tolerant Probabilistically Shaped QAM over 2824-km Dispersion-Managed Fiber

no code implementations9 Dec 2020 Junho Cho, Xi Chen, Greg Raybon, Di Che, Ellsworth Burrows, Robert Tkach

By tailoring probabilistic constellation shaping (PCS) for nonlinearity tolerance, we experimentally demonstrate up to 1. 1 dB increase in signal-to-noise ratio (SNR) and 6. 4% increase in total net data rate (NDR) compared to linear-channel-optimized PCS on a 2824-km dispersion-managed wavelength-division multiplexed (WDM) optical fiber link.

Bayesian optimization assisted unsupervised learning for efficient intra-tumor partitioning in MRI and survival prediction for glioblastoma patients

no code implementations5 Dec 2020 YiFan Li, Chao Li, Stephen Price, Carola-Bibiane Schönlieb, Xi Chen

Although successful in tumor sub-region segmentation and survival prediction, radiomics based on machine learning algorithms, is challenged by its robustness, due to the vague intermediate process and track changes.

Survival Prediction

Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance

no code implementations9 Nov 2020 Xiao Gong, Xi Chen, Wei Chen

Video surveillance is gaining increasing popularity to assist in railway intrusion detection in recent years.

Few-Shot Learning Intrusion Detection

Distant Supervision for E-commerce Query Segmentation via Attention Network

no code implementations9 Nov 2020 Zhao Li, Donghui Ding, Pengcheng Zou, Yu Gong, Xi Chen, Ji Zhang, Jianliang Gao, Youxi Wu, Yucong Duan

The booming online e-commerce platforms demand highly accurate approaches to segment queries that carry the product requirements of consumers.

An Industry Evaluation of Embedding-based Entity Alignment

1 code implementation COLING 2020 Ziheng Zhang, Jiaoyan Chen, Xi Chen, Hualuo Liu, Yuejia Xiang, Bo Liu, Yefeng Zheng

Embedding-based entity alignment has been widely investigated in recent years, but most proposed methods still rely on an ideal supervised learning setting with a large number of unbiased seed mappings for training and validation, which significantly limits their usage.

Entity Alignment Knowledge Graphs

Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance

no code implementations EMNLP (Eval4NLP) 2020 Xi Chen, Nan Ding, Tomer Levinboim, Radu Soricut

Recent advances in automatic evaluation metrics for text have shown that deep contextualized word representations, such as those generated by BERT encoders, are helpful for designing metrics that correlate well with human judgements.

Text Generation

DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis

1 code implementation3 Oct 2020 Chuheng Zhang, Yuanqi Li, Xi Chen, Yifei Jin, Pingzhong Tang, Jian Li

Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns.

Feature Selection

Privacy-Preserving Dynamic Personalized Pricing with Demand Learning

no code implementations27 Sep 2020 Xi Chen, David Simchi-Levi, Yining Wang

In this paper, we consider a dynamic pricing problem over $T$ time periods with an \emph{unknown} demand function of posted price and personalized information.

Experimental Demonstration of 4,294,967,296-QAM Based Y-00 Quantum Stream Cipher Carrying 160-Gb/s 16-QAM Signals

no code implementations23 Sep 2020 Xi Chen, Ken Tanizawa, Peter Winzer, Po Dong, Junho Cho, Fumio Futami, Kentaro Kato, Argishti Melikyan, Kw Kim

We demonstrate a 4, 294, 967, 296-ary quadrature amplitude modulation (QAM) based Y-00 quantum stream cipher system carrying 160-Gb/s 16-QAM signal transmitted over 320-km SSMF.

Finding Influential Instances for Distantly Supervised Relation Extraction

no code implementations17 Sep 2020 Zifeng Wang, Rui Wen, Xi Chen, Shao-Lun Huang, Ningyu Zhang, Yefeng Zheng

Distant supervision has been demonstrated to be highly beneficial to enhance relation extraction models, but it often suffers from high label noise.

Relation Extraction

Automated Stroke Rehabilitation Assessment using Wearable Accelerometers in Free-Living Environments

no code implementations17 Sep 2020 Xi Chen, Yu Guan, Jian-Qing Shi, Xiu-Li Du, Janet Eyre

Stroke is known as a major global health problem, and for stroke survivors it is key to monitor the recovery levels.

Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback

1 code implementation NeurIPS 2020 Zifeng Wang, Xi Chen, Rui Wen, Shao-Lun Huang, Ercan E. Kuruoglu, Yefeng Zheng

Counterfactual learning for dealing with missing-not-at-random data (MNAR) is an intriguing topic in the recommendation literature since MNAR data are ubiquitous in modern recommender systems.

Recommendation Systems

Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks

no code implementations6 Sep 2020 Zifeng Wang, Rui Wen, Xi Chen, Shilei Cao, Shao-Lun Huang, Buyue Qian, Yefeng Zheng

We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs).

Graph Convolutional Network Graph Representation Learning

On the Sample Complexity of Reinforcement Learning with Policy Space Generalization

no code implementations17 Aug 2020 Wenlong Mou, Zheng Wen, Xi Chen

To avoid such undesirable dependence on the state and action space sizes, this paper proposes a new notion of eluder dimension for the policy space, which characterizes the intrinsic complexity of policy learning in an arbitrary Markov Decision Process (MDP).

Transformer with Bidirectional Decoder for Speech Recognition

no code implementations11 Aug 2020 Xi Chen, Songyang Zhang, Dandan song, Peng Ouyang, Shouyi Yin

To demonstrate our proposed speech transformer with a bidirectional decoder(STBD), we conduct extensive experiments on the AISHELL-1 dataset.

Data Augmentation Speech Recognition

Variable Skipping for Autoregressive Range Density Estimation

1 code implementation ICML 2020 Eric Liang, Zongheng Yang, Ion Stoica, Pieter Abbeel, Yan Duan, Xi Chen

In this paper, we explore a technique, variable skipping, for accelerating range density estimation over deep autoregressive models.

Data Augmentation Density Estimation

Curves of maximal moduli on K3 surfaces

no code implementations3 Jul 2020 Xi Chen, Frank Gounelas

We prove that if $X$ is a complex projective K3 surface and $g>0$, then there exist infinitely many families of curves of geometric genus $g$ on $X$ with maximal, i. e., $g$-dimensional, variation in moduli.

Algebraic Geometry 14J28, 14N35, 14G17

NeuroCard: One Cardinality Estimator for All Tables

1 code implementation15 Jun 2020 Zongheng Yang, Amog Kamsetty, Sifei Luan, Eric Liang, Yan Duan, Xi Chen, Ion Stoica

Query optimizers rely on accurate cardinality estimates to produce good execution plans.

Non-iterative Simultaneous Rigid Registration Method for Serial Sections of Biological Tissue

no code implementations11 May 2020 Chang Shu, Xi Chen, Qiwei Xie, Chi Xiao, Hua Han

In this paper, we propose a novel non-iterative algorithm to simultaneously estimate optimal rigid transformation for serial section images, which is a key component in volume reconstruction of serial sections of biological tissue.

Learning and Testing Junta Distributions with Subcube Conditioning

no code implementations26 Apr 2020 Xi Chen, Rajesh Jayaram, Amit Levi, Erik Waingarten

The main contribution is an algorithm for finding relevant coordinates in a $k$-junta distribution with subcube conditioning [BC18, CCKLW20].

DAN: A Deformation-Aware Network for Consecutive Biomedical Image Interpolation

no code implementations23 Apr 2020 Zejin Wang, Guoqing Li, Xi Chen, Hua Han

The continuity of biological tissue between consecutive biomedical images makes it possible for the video interpolation algorithm, to recover large area defects and tears that are common in biomedical images.

Distributed Estimation for Principal Component Analysis: an Enlarged Eigenspace Analysis

no code implementations5 Apr 2020 Xi Chen, Jason D. Lee, He Li, Yun Yang

To abandon this eigengap assumption, we consider a new route in our analysis: instead of exactly identifying the top-$L$-dim eigenspace, we show that our estimator is able to cover the targeted top-$L$-dim population eigenspace.

Dimension Independent Generalization Error by Stochastic Gradient Descent

no code implementations25 Mar 2020 Xi Chen, Qiang Liu, Xin T. Tong

One classical canon of statistics is that large models are prone to overfitting, and model selection procedures are necessary for high dimensional data.

Model Selection

Uncertainty Quantification for Demand Prediction in Contextual Dynamic Pricing

no code implementations16 Mar 2020 Yining Wang, Xi Chen, Xiangyu Chang, Dongdong Ge

In this paper, using the problem of demand function prediction in dynamic pricing as the motivating example, we study the problem of constructing accurate confidence intervals for the demand function.

Resolution Adaptive Networks for Efficient Inference

1 code implementation CVPR 2020 Le Yang, Yizeng Han, Xi Chen, Shiji Song, Jifeng Dai, Gao Huang

Adaptive inference is an effective mechanism to achieve a dynamic tradeoff between accuracy and computational cost in deep networks.

Fixed-Support Wasserstein Barycenters: Computational Hardness and Fast Algorithm

no code implementations NeurIPS 2020 Tianyi Lin, Nhat Ho, Xi Chen, Marco Cuturi, Michael. I. Jordan

We study the fixed-support Wasserstein barycenter problem (FS-WBP), which consists in computing the Wasserstein barycenter of $m$ discrete probability measures supported on a finite metric space of size $n$.

Online Covariance Matrix Estimation in Stochastic Gradient Descent

no code implementations10 Feb 2020 Wanrong Zhu, Xi Chen, Wei Biao Wu

This approach fits in an online setting and takes full advantage of SGD: efficiency in computation and memory.

ALPINE: Active Link Prediction using Network Embedding

no code implementations4 Feb 2020 Xi Chen, Bo Kang, Jefrey Lijffijt, Tijl De Bie

Often, the link status of a node pair can be queried, which can be used as additional information by the link prediction algorithm.

Active Learning Experimental Design +2

On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond

no code implementations25 Jan 2020 Zifeng Wang, Xi Chen, Rui Wen, Shao-Lun Huang

Observed events in recommendation are consequence of the decisions made by a policy, thus they are usually selectively labeled, namely the data are Missing Not At Random (MNAR), which often causes large bias to the estimate of true outcomes risk.

Fairness

Correcting Knowledge Base Assertions

1 code implementation19 Jan 2020 Jiaoyan Chen, Xi Chen, Ian Horrocks, Ernesto Jimenez-Ruiz, Erik B. Myklebus

The usefulness and usability of knowledge bases (KBs) is often limited by quality issues.

Adaptive Discrete Smoothing for High-Dimensional and Nonlinear Panel Data

no code implementations30 Dec 2019 Xi Chen, Ye Luo, Martin Spindler

In this paper we develop a data-driven smoothing technique for high-dimensional and non-linear panel data models.

EdgeDRNN: Enabling Low-latency Recurrent Neural Network Edge Inference

no code implementations22 Dec 2019 Chang Gao, Antonio Rios-Navarro, Xi Chen, Tobi Delbruck, Shih-Chii Liu

This paper presents a Gated Recurrent Unit (GRU) based recurrent neural network (RNN) accelerator called EdgeDRNN designed for portable edge computing.

Edge-computing

Small-footprint Keyword Spotting with Graph Convolutional Network

no code implementations11 Dec 2019 Xi Chen, Shouyi Yin, Dandan song, Peng Ouyang, Leibo Liu, Shaojun Wei

Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices.

Graph Convolutional Network Small-Footprint Keyword Spotting

Online EXP3 Learning in Adversarial Bandits with Delayed Feedback

no code implementations NeurIPS 2019 Ilai Bistritz, Zhengyuan Zhou, Xi Chen, Nicholas Bambos, Jose Blanchet

An adversary chooses the cost of each arm in a bounded interval, and a sequence of feedback delays \left\{ d_{t}\right\} that are unknown to the player.

Random Restrictions of High-Dimensional Distributions and Uniformity Testing with Subcube Conditioning

no code implementations17 Nov 2019 Clément L. Canonne, Xi Chen, Gautam Kamath, Amit Levi, Erik Waingarten

We give a nearly-optimal algorithm for testing uniformity of distributions supported on $\{-1, 1\}^n$, which makes $\tilde O (\sqrt{n}/\varepsilon^2)$ queries to a subcube conditional sampling oracle (Bhattacharyya and Chakraborty (2018)).

Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem

no code implementations27 Oct 2019 Zhengxuan Ling, Xinyu Tao, Yu Zhang, Xi Chen

Based on samples of a 10 city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution.

Traveling Salesman Problem

Thresholding Bandit Problem with Both Duels and Pulls

no code implementations14 Oct 2019 Yichong Xu, Xi Chen, Aarti Singh, Artur Dubrawski

The Thresholding Bandit Problem (TBP) aims to find the set of arms with mean rewards greater than a given threshold.

Robust Dynamic Assortment Optimization in the Presence of Outlier Customers

no code implementations9 Oct 2019 Xi Chen, Akshay Krishnamurthy, Yining Wang

The main question investigated in this paper is model mis-specification under the $\varepsilon$-contamination model, which is a fundamental model in robust statistics and machine learning.

Skew-Explore: Learn faster in continuous spaces with sparse rewards

no code implementations25 Sep 2019 Xi Chen, Yuan Gao, Ali Ghadirzadeh, Marten Bjorkman, Ginevra Castellano, Patric Jensfelt

In this work, we introduce an exploration approach based on maximizing the entropy of the visited states while learning a goal-conditioned policy.

Learning Visual Relation Priors for Image-Text Matching and Image Captioning with Neural Scene Graph Generators

no code implementations22 Sep 2019 Kuang-Huei Lee, Hamid Palangi, Xi Chen, Houdong Hu, Jianfeng Gao

In this work, we tackle two fundamental language-and-vision tasks: image-text matching and image captioning, and demonstrate that neural scene graph generators can learn effective visual relation features to facilitate grounding language to visual relations and subsequently improve the two end applications.

Image Captioning Text Matching

Adversarial Feature Training for Generalizable Robotic Visuomotor Control

no code implementations17 Sep 2019 Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

Deep reinforcement learning (RL) has enabled training action-selection policies, end-to-end, by learning a function which maps image pixels to action outputs.

Transfer Learning

UER: An Open-Source Toolkit for Pre-training Models

1 code implementation IJCNLP 2019 Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.

Bayesian posterior repartitioning for nested sampling

no code implementations13 Aug 2019 Xi Chen, Farhan Feroz, Michael Hobson

We show through numerical examples that this Bayesian PR (BPR) method provides a very robust, self-adapting and computationally efficient `hands-off' solution to the problem of unrepresentative priors in Bayesian inference using NS.

Bayesian Inference Unity

Efficient average-case population recovery in the presence of insertions and deletions

no code implementations12 Jul 2019 Frank Ban, Xi Chen, Rocco A. Servedio, Sandip Sinha

In this problem, there is an unknown distribution $\cal{D}$ over $s$ unknown source strings $x^1,\dots, x^s \in \{0, 1\}^n$, and each sample is independently generated by drawing some $x^i$ from $\cal{D}$ and returning an independent trace of $x^i$.

Evaluating Protein Transfer Learning with TAPE

4 code implementations NeurIPS 2019 Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S. Song

Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets and standardized evaluation techniques.

Representation Learning Transfer Learning

Distributed High-dimensional Regression Under a Quantile Loss Function

no code implementations13 Jun 2019 Xi Chen, Weidong Liu, Xiaojun Mao, Zhuoyi Yang

This paper studies distributed estimation and support recovery for high-dimensional linear regression model with heavy-tailed noise.

Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features

no code implementations NAACL 2019 Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin

Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company{'}s customer service agents have the option of escalating their complaints by filing grievances with a government authority.

Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning

1 code implementation31 May 2019 Yang Liu, Yunan Luo, Yuanyi Zhong, Xi Chen, Qiang Liu, Jian Peng

Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications.

Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules

3 code implementations14 May 2019 Daniel Ho, Eric Liang, Ion Stoica, Pieter Abbeel, Xi Chen

A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations.

Image Augmentation

Deep Unsupervised Cardinality Estimation

1 code implementation10 May 2019 Zongheng Yang, Eric Liang, Amog Kamsetty, Chenggang Wu, Yan Duan, Xi Chen, Pieter Abbeel, Joseph M. Hellerstein, Sanjay Krishnan, Ion Stoica

To produce a truly usable estimator, we develop a Monte Carlo integration scheme on top of autoregressive models that can efficiently handle range queries with dozens of dimensions or more.

Density Estimation

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

no code implementations4 May 2019 Yingkai Li, Yining Wang, Xi Chen, Yuan Zhou

Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks.

Decision Making Multi-Armed Bandits +1

On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics

no code implementations30 Apr 2019 Xi Chen, Simon S. Du, Xin T. Tong

In this paper, using intuitions from stochastic differential equations, we provide a direct analysis for the hitting times of SGLD to the first and second order stationary points.

Stochastic Optimization

Towards Pricing Financial Derivatives with an IBM Quantum Computer

1 code implementation11 Apr 2019 Ana Martin, Bruno Candelas, Ángel Rodríguez-Rozas, José D. Martín-Guerrero, Xi Chen, Lucas Lamata, Román Orús, Enrique Solano, Mikel Sanz

Pricing interest-rate financial derivatives is a major problem in finance, in which it is crucial to accurately reproduce the time-evolution of interest rates.

Quantum Physics Mesoscale and Nanoscale Physics

Context-Based Dynamic Pricing with Online Clustering

no code implementations17 Feb 2019 Sentao Miao, Xi Chen, Xiuli Chao, Jiaxi Liu, Yidong Zhang

By clustering data and identifying products that have similar demand patterns, we utilize sales data from products within the same cluster to improve demand estimation and allow for better pricing decisions.

Online Clustering

Bayesian surrogate learning in dynamic simulator-based regression problems

no code implementations25 Jan 2019 Xi Chen, Mike Hobson

The estimation of unknown values of parameters (or hidden variables, control variables) that characterise a physical system often relies on the comparison of measured data with synthetic data produced by some numerical simulator of the system as the parameter values are varied.

Boundary-Aware Network for Fast and High-Accuracy Portrait Segmentation

1 code implementation12 Jan 2019 Xi Chen, Donglian Qi, Jianxin Shen

Compared with other semantic segmentation tasks, portrait segmentation requires both higher precision and faster inference speed.

Portrait Segmentation Semantic Segmentation

Large-Scale Markov Decision Problems via the Linear Programming Dual

no code implementations6 Jan 2019 Yasin Abbasi-Yadkori, Peter L. Bartlett, Xi Chen, Alan Malek

Moreover, we propose an efficient algorithm, scaling with the size of the subspace but not the state space, that is able to find a policy with low excess loss relative to the best policy in this class.

Parallelized Interactive Machine Learning on Autonomous Vehicles

no code implementations23 Dec 2018 Xi Chen, Caylin Hickey

In this work, we use a human demonstration approach to speed up training for learning features and use the resulting pre-trained model to replace the neural network in the deep RL Deep Q-Network (DQN), followed by human interaction to further refine the model.

Autonomous Vehicles

A Method to Facilitate Cancer Detection and Type Classification from Gene Expression Data using a Deep Autoencoder and Neural Network

no code implementations20 Dec 2018 Xi Chen, Jin Xie, Qingcong Yuan

Here we present models of deep learning (DL) and apply them to gene expression data for the diagnosis and categorization of cancer.

General Classification

Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models

no code implementations NeurIPS 2018 Yining Wang, Xi Chen, Yuan Zhou

In this paper we consider the dynamic assortment selection problem under an uncapacitated multinomial-logit (MNL) model.

Distributed Inference for Linear Support Vector Machine

no code implementations29 Nov 2018 Xiaozhou Wang, Zhuoyi Yang, Xi Chen, Weidong Liu

In this paper, we propose a multi-round distributed linear-type (MDL) estimator for conducting inference for linear SVM.

First-order Newton-type Estimator for Distributed Estimation and Inference

no code implementations28 Nov 2018 Xi Chen, Weidong Liu, Yichen Zhang

The key component in our method is the proposal of a computationally efficient estimator of $\Sigma^{-1} w$, where $\Sigma$ is the population Hessian matrix and $w$ is any given vector.

Meta-Learning for Multi-objective Reinforcement Learning

no code implementations8 Nov 2018 Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt

Multi-objective reinforcement learning (MORL) is the generalization of standard reinforcement learning (RL) approaches to solve sequential decision making problems that consist of several, possibly conflicting, objectives.

Continuous Control Decision Making +1

Learning from Demonstration in the Wild

no code implementations8 Nov 2018 Feryal Behbahani, Kyriacos Shiarlis, Xi Chen, Vitaly Kurin, Sudhanshu Kasewa, Ciprian Stirbu, João Gomes, Supratik Paul, Frans A. Oliehoek, João Messias, Shimon Whiteson

Learning from demonstration (LfD) is useful in settings where hand-coding behaviour or a reward function is impractical.

Dynamic Assortment Optimization with Changing Contextual Information

no code implementations31 Oct 2018 Xi Chen, Yining Wang, Yuan Zhou

To this end, we develop an upper confidence bound (UCB) based policy and establish the regret bound on the order of $\widetilde O(d\sqrt{T})$, where $d$ is the dimension of the feature and $\widetilde O$ suppresses logarithmic dependence.

Combinatorial Optimization

Quantile Regression Under Memory Constraint

no code implementations18 Oct 2018 Xi Chen, Weidong Liu, Yichen Zhang

This paper proposes a computationally efficient method, which only requires an initial QR estimator on a small batch of data and then successively refines the estimator via multiple rounds of aggregations.

Distributed Computing

Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective

no code implementations8 Oct 2018 Yunlun Yang, Yu Gong, Xi Chen

With the development of dialog techniques, conversational search has attracted more and more attention as it enables users to interact with the search engine in a natural and efficient manner.

Conversational Search Natural Language Understanding +2

Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding

no code implementations EMNLP 2018 Guanying Wang, Wen Zhang, Ruoxu Wang, Yalin Zhou, Xi Chen, Wei zhang, Hai Zhu, Huajun Chen

This paper proposes a label-free distant supervision method, which makes no use of the relation labels under this inadequate assumption, but only uses the prior knowledge derived from the KG to supervise the learning of the classifier directly and softly.

Knowledge Graph Embedding Relation Extraction +1

Shape-Enforcing Operators for Point and Interval Estimators

no code implementations4 Sep 2018 Xi Chen, Victor Chernozhukov, Iván Fernández-Val, Scott Kostyshak, Ye Luo

A common problem in econometrics, statistics, and machine learning is to estimate and make inference on functions that satisfy shape restrictions.

Learning to Compose over Tree Structures via POS Tags

no code implementations18 Aug 2018 Gehui Shen, Zhi-Hong Deng, Ting Huang, Xi Chen

Recursive Neural Network (RecNN), a type of models which compose words or phrases recursively over syntactic tree structures, has been proven to have superior ability to obtain sentence representation for a variety of NLP tasks.

POS Semantic Composition +2

Quantized Single-Ion-Channel Hodgkin-Huxley Model for Quantum Neurons

no code implementations27 Jul 2018 Tasio Gonzalez-Raya, Xiao-Hang Cheng, Iñigo L. Egusquiza, Xi Chen, Mikel Sanz, Enrique Solano

This reduced version is essentially a classical memristor, a resistor whose resistance depends on the history of electric signals that have crossed it, coupled to a voltage source and a capacitor.

Experimental Implementation of a Quantum Autoencoder via Quantum Adders

no code implementations27 Jul 2018 Yongcheng Ding, Lucas Lamata, Mikel Sanz, Xi Chen, Enrique Solano

Quantum autoencoders allow for reducing the amount of resources in a quantum computation by mapping the original Hilbert space onto a reduced space with the relevant information.

Dynamic Assortment Selection under the Nested Logit Models

no code implementations27 Jun 2018 Xi Chen, Chao Shi, Yining Wang, Yuan Zhou

One key challenge is that utilities of products are unknown to the seller and need to be learned.

A Novel Framework for Recurrent Neural Networks with Enhancing Information Processing and Transmission between Units

no code implementations2 Jun 2018 Xi Chen, Zhi-Hong Deng, Gehui Shen, Ting Huang

This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units.

General Classification Image Classification +2

Reinforcement Learning based QoS/QoE-aware Service Function Chaining in Software-Driven 5G Slices

no code implementations6 Apr 2018 Xi Chen, Zonghang Li, Yupeng Zhang, Ruiming Long, Hongfang Yu, Xiaojiang Du, Mohsen Guizani

With the ever growing diversity of devices and applications that will be connected to 5G networks, flexible and agile service orchestration with acknowledged QoE that satisfies end-user's functional and QoS requirements is necessary.

Stacked Cross Attention for Image-Text Matching

3 code implementations ECCV 2018 Kuang-Huei Lee, Xi Chen, Gang Hua, Houdong Hu, Xiaodong He

Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable.

Cross-Modal Retrieval Image Retrieval +1

Web-Scale Responsive Visual Search at Bing

no code implementations14 Feb 2018 Houdong Hu, Yan Wang, Linjun Yang, Pavel Komlev, Li Huang, Xi Chen, Jiapei Huang, Ye Wu, Meenaz Merchant, Arun Sacheti

In this paper, we introduce a web-scale general visual search system deployed in Microsoft Bing.

Learning-To-Rank

Tracking Multiple Moving Objects Using Unscented Kalman Filtering Techniques

no code implementations5 Feb 2018 Xi Chen, Xiao Wang, Jianhua Xuan

Considering the ambiguity caused by the occlusion among multiple moving objects, we apply an unscented Kalman filtering (UKF) technique for reliable object detection and tracking.

Multiple Object Tracking Object Detection

Hierarchical Spatial Transformer Network

no code implementations29 Jan 2018 Chang Shu, Xi Chen, Qiwei Xie, Hua Han

Computer vision researchers have been expecting that neural networks have spatial transformation ability to eliminate the interference caused by geometric distortion for a long time.

Optical Flow Estimation

PixelSNAIL: An Improved Autoregressive Generative Model

6 code implementations ICML 2018 Xi Chen, Nikhil Mishra, Mostafa Rohaninejad, Pieter Abbeel

Autoregressive generative models consistently achieve the best results in density estimation tasks involving high dimensional data, such as images or audio.

Density Estimation Image Generation +1

Wasserstein Distributionally Robust Optimization and Variation Regularization

no code implementations17 Dec 2017 Rui Gao, Xi Chen, Anton J. Kleywegt

Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect.

Stochastic Optimization

Safer Classification by Synthesis

no code implementations22 Nov 2017 William Wang, Angelina Wang, Aviv Tamar, Xi Chen, Pieter Abbeel

We posit that a generative approach is the natural remedy for this problem, and propose a method for classification using generative models.

General Classification

HodgeRank with Information Maximization for Crowdsourced Pairwise Ranking Aggregation

no code implementations16 Nov 2017 Qianqian Xu, Jiechao Xiong, Xi Chen, Qingming Huang, Yuan YAO

Recently, crowdsourcing has emerged as an effective paradigm for human-powered large scale problem solving in various domains.

Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single Image Super-Resolution

no code implementations15 Nov 2017 Yongliang Tang, Weiguo Gong, Xi Chen, Weihong Li

With exploiting contextual information over large image regions in an efficient way, the deep convolutional neural network has shown an impressive performance for single image super-resolution (SR).

Image Super-Resolution

Automatic Conflict Detection in Police Body-Worn Audio

no code implementations14 Nov 2017 Alistair Letcher, Jelena Trišović, Collin Cademartori, Xi Chen, Jason Xu

Automatic conflict detection has grown in relevance with the advent of body-worn technology, but existing metrics such as turn-taking and overlap are poor indicators of conflict in police-public interactions.

Meta Learning Shared Hierarchies

2 code implementations ICLR 2018 Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel, John Schulman

We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps.

Legged Robots Meta-Learning

Constructing multi-modality and multi-classifier radiomics predictive models through reliable classifier fusion

no code implementations4 Oct 2017 Zhiguo Zhou, Zhi-Jie Zhou, Hongxia Hao, Shulong Li, Xi Chen, You Zhang, Michael Folkert, Jing Wang

First, the predictive performance of the model may be reduced when features extracted from an individual imaging modality are blindly combined into a single predictive model.

A Note on a Tight Lower Bound for MNL-Bandit Assortment Selection Models

no code implementations18 Sep 2017 Xi Chen, Yining Wang

In this short note we consider a dynamic assortment planning problem under the capacitated multinomial logit (MNL) bandit model.

Review of Tensor Network Contraction Approaches

1 code implementation30 Aug 2017 Shi-Ju Ran, Emanuele Tirrito, Cheng Peng, Xi Chen, Gang Su, Maciej Lewenstein

One goal is to provide a systematic introduction of TN contraction algorithms (motivations, implementations, relations, implications, etc.

Computational Physics Statistical Mechanics Strongly Correlated Electrons Applied Physics Quantum Physics

Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures

no code implementations9 Aug 2017 Xi Chen, Yining Wang, Yu-Xiang Wang

We consider a non-stationary sequential stochastic optimization problem, in which the underlying cost functions change over time under a variation budget constraint.

Stochastic Optimization

An Effective Training Method For Deep Convolutional Neural Network

no code implementations31 Jul 2017 Yang Jiang, Zeyang Dou, Qun Hao, Jie Cao, Kun Gao, Xi Chen

In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks.

Object Recognition

A Nearly Instance Optimal Algorithm for Top-k Ranking under the Multinomial Logit Model

no code implementations25 Jul 2017 Xi Chen, Yuanzhi Li, Jieming Mao

We study the active learning problem of top-$k$ ranking from multi-wise comparisons under the popular multinomial logit model.

Active Learning

A Simple Neural Attentive Meta-Learner

3 code implementations ICLR 2018 Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel

Deep neural networks excel in regimes with large amounts of data, but tend to struggle when data is scarce or when they need to adapt quickly to changes in the task.

Few-Shot Image Classification Meta-Learning

High-fidelity adiabatic quantum computation using the intrinsic Hamiltonian of a spin system: Application to the experimental factorization of 291311

no code implementations25 Jun 2017 Zhaokai Li, Nikesh S. Dattani, Xi Chen, Xiaomei Liu, Hengyan Wang, Richard Tanburn, Hongwei Chen, Xinhua Peng, Jiangfeng Du

In previous implementations of adiabatic quantum algorithms using spin systems, the average Hamiltonian method with Trotter's formula was conventionally adopted to generate an effective instantaneous Hamiltonian that simulates an adiabatic passage.

Quantum Physics

Adaptive Multiple-Arm Identification

no code implementations ICML 2017 Jiecao Chen, Xi Chen, Qin Zhang, Yuan Zhou

We study the problem of selecting $K$ arms with the highest expected rewards in a stochastic $n$-armed bandit game.

Equivalence Between Policy Gradients and Soft Q-Learning

no code implementations21 Apr 2017 John Schulman, Xi Chen, Pieter Abbeel

A partial explanation may be that $Q$-learning methods are secretly implementing policy gradient updates: we show that there is a precise equivalence between $Q$-learning and policy gradient methods in the setting of entropy-regularized reinforcement learning, that "soft" (entropy-regularized) $Q$-learning is exactly equivalent to a policy gradient method.

Policy Gradient Methods Q-Learning

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

16 code implementations10 Mar 2017 Tim Salimans, Jonathan Ho, Xi Chen, Szymon Sidor, Ilya Sutskever

We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients.

Atari Games Q-Learning

Estimation of the volume of the left ventricle from MRI images using deep neural networks

1 code implementation13 Feb 2017 Fangzhou Liao, Xi Chen, Xiaolin Hu, Sen Song

In 2016, Kaggle organized a competition to estimate the volume of LV from MRI images.

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

7 code implementations19 Jan 2017 Tim Salimans, Andrej Karpathy, Xi Chen, Diederik P. Kingma

1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training.

Image Generation

Bayesian Decision Process for Cost-Efficient Dynamic Ranking via Crowdsourcing

no code implementations21 Dec 2016 Xi Chen, Kevin Jiao, Qihang Lin

Rank aggregation based on pairwise comparisons over a set of items has a wide range of applications.

Improved Variational Inference with Inverse Autoregressive Flow

1 code implementation NeurIPS 2016 Durk P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, Max Welling

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.

Ranked #29 on Image Generation on CIFAR-10 (bits/dimension metric)

Image Generation Variational Inference

On the Recursive Teaching Dimension of VC Classes

no code implementations NeurIPS 2016 Xi Chen, Yu Cheng, Bo Tang

This is the first upper bound for $RTD(C)$ that depends only on $VCD(C)$, independent of the size of the concept class $|C|$ and its~domain size $n$.

#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning

3 code implementations NeurIPS 2017 Haoran Tang, Rein Houthooft, Davis Foote, Adam Stooke, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

In this work, we describe a surprising finding: a simple generalization of the classic count-based approach can reach near state-of-the-art performance on various high-dimensional and/or continuous deep RL benchmarks.

Atari Games Continuous Control

RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning

15 code implementations9 Nov 2016 Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel

The activations of the RNN store the state of the "fast" RL algorithm on the current (previously unseen) MDP.

Variational Lossy Autoencoder

no code implementations8 Nov 2016 Xi Chen, Diederik P. Kingma, Tim Salimans, Yan Duan, Prafulla Dhariwal, John Schulman, Ilya Sutskever, Pieter Abbeel

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification.

Density Estimation Image Generation +1

Statistical Inference for Model Parameters in Stochastic Gradient Descent

no code implementations27 Oct 2016 Xi Chen, Jason D. Lee, Xin T. Tong, Yichen Zhang

Second, for high-dimensional linear regression, using a variant of the SGD algorithm, we construct a debiased estimator of each regression coefficient that is asymptotically normal.

The Role of Context Selection in Object Detection

no code implementations9 Sep 2016 Ruichi Yu, Xi Chen, Vlad I. Morariu, Larry S. Davis

We investigate the reasons why context in object detection has limited utility by isolating and evaluating the predictive power of different context cues under ideal conditions in which context provided by an oracle.

Object Detection

Improving Variational Inference with Inverse Autoregressive Flow

8 code implementations15 Jun 2016 Diederik P. Kingma, Tim Salimans, Rafal Jozefowicz, Xi Chen, Ilya Sutskever, Max Welling

The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.

Variational Inference

InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

35 code implementations NeurIPS 2016 Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, Pieter Abbeel

This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.

Image Generation Representation Learning +2

VIME: Variational Information Maximizing Exploration

2 code implementations NeurIPS 2016 Rein Houthooft, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel

While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in high-dimensional deep RL scenarios.

Continuous Control Variational Inference

Competitive analysis of the top-K ranking problem

no code implementations12 May 2016 Xi Chen, Sivakanth Gopi, Jieming Mao, Jon Schneider

In particular, we present a linear time algorithm for the top-$K$ problem which has a competitive ratio of $\tilde{O}(\sqrt{n})$; i. e. to solve any instance of top-$K$, our algorithm needs at most $\tilde{O}(\sqrt{n})$ times as many samples needed as the best possible algorithm for that instance (in contrast, all previous known algorithms for the top-$K$ problem have competitive ratios of $\tilde{\Omega}(n)$ or worse).

Recommendation Systems

Building a Dataset for Possessions Identification in Text

no code implementations LREC 2016 Carmen Banea, Xi Chen, Rada Mihalcea

Just as industrialization matured from mass production to customization and personalization, so has the Web migrated from generic content to public disclosures of one{'}s most intimately held thoughts, opinions and beliefs.

Benchmarking Deep Reinforcement Learning for Continuous Control

15 code implementations22 Apr 2016 Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel

Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.

Atari Games Continuous Control

Generating Discriminative Object Proposals via Submodular Ranking

no code implementations11 Feb 2016 Yangmuzi Zhang, Zhuolin Jiang, Xi Chen, Larry S. Davis

Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation.

Object Proposal Generation Semantic Segmentation

Sequential Optimization for Efficient High-Quality Object Proposal Generation

no code implementations14 Nov 2015 Ziming Zhang, Yun Liu, Xi Chen, Yanjun Zhu, Ming-Ming Cheng, Venkatesh Saligrama, Philip H. S. Torr

We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.

Object Proposal Generation

Unsupervised Network Pretraining via Encoding Human Design

no code implementations19 Feb 2015 Ming-Yu Liu, Arun Mallya, Oncel C. Tuzel, Xi Chen

Our idea is to pretrain the network through the task of replicating the process of hand-designed feature extraction.

Object Recognition

Statistical Decision Making for Optimal Budget Allocation in Crowd Labeling

no code implementations12 Mar 2014 Xi Chen, Qihang Lin, Dengyong Zhou

In crowd labeling, a large amount of unlabeled data instances are outsourced to a crowd of workers.

Decision Making

Variance Reduction for Stochastic Gradient Optimization

no code implementations NeurIPS 2013 Chong Wang, Xi Chen, Alexander J. Smola, Eric P. Xing

We demonstrate how to construct the control variate for two practical problems using stochastic gradient optimization.

Variational Inference

Evaluating computational models of explanation using human judgments

no code implementations26 Sep 2013 Michael Pacer, Joseph Williams, Xi Chen, Tania Lombrozo, Thomas Griffiths

We evaluate four computational models of explanation in Bayesian networks by comparing model predictions to human judgments.

Classifying and Visualizing Motion Capture Sequences using Deep Neural Networks

no code implementations17 Jun 2013 Kyunghyun Cho, Xi Chen

The gesture recognition using motion capture data and depth sensors has recently drawn more attention in vision recognition.

Gesture Recognition