Search Results for author: Jian Li

Found 177 papers, 46 papers with code

MTRec: Multi-Task Learning over BERT for News Recommendation

1 code implementation Findings (ACL) 2022 Qiwei Bi, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, Hanfang Yang

With the adoption of large pre-trained models like BERT in news recommendation, the above way to incorporate multi-field information may encounter challenges: the shallow feature encoding to compress the category and entity information is not compatible with the deep BERT encoding.

Multi-Task Learning News Recommendation

Natural Language Processing Meets Quantum Physics: A Survey and Categorization

no code implementations EMNLP 2021 Sixuan Wu, Jian Li, Peng Zhang, Yue Zhang

Recent research has investigated quantum NLP, designing algorithms that process natural language in quantum computers, and also quantum-inspired algorithms that improve NLP performance on classical computers.

Controlled Text Generation Using Dictionary Prior in Variational Autoencoders

no code implementations Findings (ACL) 2022 Xianghong Fang, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, Dit-yan Yeung

While variational autoencoders (VAEs) have been widely applied in text generation tasks, they are troubled by two challenges: insufficient representation capacity and poor controllability.

Contrastive Learning Language Modelling +2

GLIME: General, Stable and Local LIME Explanation

1 code implementation27 Nov 2023 Zeren Tan, Yang Tian, Jian Li

Additionally, LIME's sampling neighborhood is non-local and biased towards the reference, resulting in poor local fidelity and sensitivity to reference choice.

Trustworthy AI: Deciding What to Decide

no code implementations21 Nov 2023 Caesar Wu, Yuan-Fang Li, Jian Li, Jingjing Xu, Bouvry Pascal

We aim to use this framework to conduct the TAI experiments by quantitive and qualitative research methods to satisfy TAI properties for the decision-making context.

Decision Making

Adversarial Preference Optimization

no code implementations14 Nov 2023 Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Nan Du

Human preference alignment is a crucial training step to improve the interaction quality of large language models (LLMs).

LCM-LoRA: A Universal Stable-Diffusion Acceleration Module

1 code implementation9 Nov 2023 Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu, Patrick von Platen, Apolinário Passos, Longbo Huang, Jian Li, Hang Zhao

Latent Consistency Models (LCMs) have achieved impressive performance in accelerating text-to-image generative tasks, producing high-quality images with minimal inference steps.

Image Generation

JOSA: Joint surface-based registration and atlas construction of brain geometry and function

no code implementations22 Oct 2023 Jian Li, Greta Tuckute, Evelina Fedorenko, Brian L. Edlow, Adrian V. Dalca, Bruce Fischl

By recognizing the mismatch between geometry and function, JOSA provides new insights into the future development of registration methods using joint analysis of the brain structure and function.

Efficient online cross-covariance monitoring with incremental SVD: An approach for the detection of emerging dependency patterns in IoT systems

no code implementations19 Oct 2023 Xinmiao Luan, Qing Zou, Jian Li, Andi Wang

The development of the manufacturing systems has made it increasingly necessary to monitor the data generated by multiple interconnected subsystems with rapid incoming of samples.

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

1 code implementation6 Oct 2023 Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, Hang Zhao

Inspired by Consistency Models (song et al.), we propose Latent Consistency Models (LCMs), enabling swift inference with minimal steps on any pre-trained LDMs, including Stable Diffusion (rombach et al).

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

no code implementations3 Oct 2023 Guojun Xiong, Jian Li

In this paper, we present Neural-Q-Whittle, a Whittle index based Q-learning algorithm for RMAB with neural network function approximation, which is an example of nonlinear two-timescale stochastic approximation with Q-function values updated on a faster timescale and Whittle indices on a slower timescale.

Multi-Armed Bandits Q-Learning

Revolutionizing Terrain-Precipitation Understanding through AI-driven Knowledge Discovery

no code implementations27 Sep 2023 Hao Xu, Yuntian Chen, Zhenzhong Zeng, Nina Li, Jian Li, Dongxiao Zhang

Advancing our understanding of climate processes in regions characterized by intricate terrain complexity is a paramount challenge in contemporary climate science, particularly in the context of global climate change.

A Real-time Faint Space Debris Detector With Learning-based LCM

no code implementations15 Sep 2023 Zherui Lu, Gangyi Wang, Xinguo Wei, Jian Li

In conclusion, the algorithm in this paper is of high speed and precision, which guarantees its promising applications in the extraction of high dynamic targets.

Interpretable and Efficient Beamforming-Based Deep Learning for Single Snapshot DOA Estimation

no code implementations14 Sep 2023 Ruxin Zheng, Shunqiao Sun, Hongshan Liu, Honglei Chen, Jian Li

We introduce an interpretable deep learning approach for direction of arrival (DOA) estimation with a single snapshot.

Compressive Sensing

A Survey on Model Compression for Large Language Models

no code implementations15 Aug 2023 Xunyu Zhu, Jian Li, Yong liu, Can Ma, Weiping Wang

As these challenges become increasingly pertinent, the field of model compression has emerged as a pivotal research area to alleviate these limitations.

Benchmarking Knowledge Distillation +2

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

no code implementations8 Aug 2023 Haomin Zhuang, Mingxian Yu, Hao Wang, Yang Hua, Jian Li, Xu Yuan

Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices.

Backdoor Attack Federated Learning

Toward Zero-shot Character Recognition: A Gold Standard Dataset with Radical-level Annotations

no code implementations1 Aug 2023 Xiaolei Diao, Daqian Shi, Jian Li, Lida Shi, Mingzhe Yue, Ruihua Qi, Chuntao Li, Hao Xu

To increase the adaptability of ACCID, we propose a splicing-based synthetic character algorithm to augment the training samples and apply an image denoising method to improve the image quality.

Image Denoising Optical Character Recognition +1

PVG: Progressive Vision Graph for Vision Recognition

no code implementations1 Aug 2023 Jiafu Wu, Jian Li, Jiangning Zhang, Boshen Zhang, Mingmin Chi, Yabiao Wang, Chengjie Wang

Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects.

graph construction

SplatFlow: Learning Multi-frame Optical Flow via Splatting

no code implementations15 Jun 2023 Bo wang, Yifan Zhang, Jian Li, Yang Yu, Zhenping Sun, Li Liu, Dewen Hu

Occlusion problem remains a key challenge in Optical Flow Estimation (OFE) despite the recent significant progress brought by deep learning in the field.

Optical Flow Estimation

Straggler-Resilient Decentralized Learning via Adaptive Asynchronous Updates

no code implementations11 Jun 2023 Guojun Xiong, Gang Yan, Shiqiang Wang, Jian Li

With the increasing demand for large-scale training of machine learning models, fully decentralized optimization methods have recently been advocated as alternatives to the popular parameter server framework.

Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization

no code implementations8 Jun 2023 Clemens JS Schaefer, Navid Lambert-Shirzad, Xiaofan Zhang, Chiachen Chou, Tom Jablin, Jian Li, Elfie Guo, Caitlin Stanton, Siddharth Joshi, Yu Emma Wang

To address this challenge, we propose a mixed-precision post training quantization (PTQ) approach that assigns different numerical precisions to tensors in a network based on their specific needs, for a reduced memory footprint and improved latency while preserving model accuracy.


Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs

no code implementations31 May 2023 Yi Sun, Xin Xu, Jian Li, Xiaochang Hu, Yifei Shi, Ling-Li Zeng

By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.

2-bit Conformer quantization for automatic speech recognition

no code implementations26 May 2023 Oleg Rybakov, Phoenix Meadowlark, Shaojin Ding, David Qiu, Jian Li, David Rim, Yanzhang He

With the large-scale training data, we obtain a 2-bit Conformer model with over 40% model size reduction against the 4-bit version at the cost of 17% relative word error rate degradation

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance

1 code implementation18 May 2023 Zheyu Zhang, Tianping Zhang, Jian Li

To this end, we provide a fine-grained analysis of bias in GBDT and demonstrate that the bias originates from 1) the systematic bias in the gain estimation of each split and 2) the bias in the split finding algorithm resulting from the use of the same data to evaluate the split improvement and determine the best split.

Feature Importance feature selection

PaLM 2 Technical Report

1 code implementation17 May 2023 Rohan Anil, Andrew M. Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos, Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, Eric Chu, Jonathan H. Clark, Laurent El Shafey, Yanping Huang, Kathy Meier-Hellstern, Gaurav Mishra, Erica Moreira, Mark Omernick, Kevin Robinson, Sebastian Ruder, Yi Tay, Kefan Xiao, Yuanzhong Xu, Yujing Zhang, Gustavo Hernandez Abrego, Junwhan Ahn, Jacob Austin, Paul Barham, Jan Botha, James Bradbury, Siddhartha Brahma, Kevin Brooks, Michele Catasta, Yong Cheng, Colin Cherry, Christopher A. Choquette-Choo, Aakanksha Chowdhery, Clément Crepy, Shachi Dave, Mostafa Dehghani, Sunipa Dev, Jacob Devlin, Mark Díaz, Nan Du, Ethan Dyer, Vlad Feinberg, Fangxiaoyu Feng, Vlad Fienber, Markus Freitag, Xavier Garcia, Sebastian Gehrmann, Lucas Gonzalez, Guy Gur-Ari, Steven Hand, Hadi Hashemi, Le Hou, Joshua Howland, Andrea Hu, Jeffrey Hui, Jeremy Hurwitz, Michael Isard, Abe Ittycheriah, Matthew Jagielski, Wenhao Jia, Kathleen Kenealy, Maxim Krikun, Sneha Kudugunta, Chang Lan, Katherine Lee, Benjamin Lee, Eric Li, Music Li, Wei Li, Yaguang Li, Jian Li, Hyeontaek Lim, Hanzhao Lin, Zhongtao Liu, Frederick Liu, Marcello Maggioni, Aroma Mahendru, Joshua Maynez, Vedant Misra, Maysam Moussalem, Zachary Nado, John Nham, Eric Ni, Andrew Nystrom, Alicia Parrish, Marie Pellat, Martin Polacek, Alex Polozov, Reiner Pope, Siyuan Qiao, Emily Reif, Bryan Richter, Parker Riley, Alex Castro Ros, Aurko Roy, Brennan Saeta, Rajkumar Samuel, Renee Shelby, Ambrose Slone, Daniel Smilkov, David R. So, Daniel Sohn, Simon Tokumine, Dasha Valter, Vijay Vasudevan, Kiran Vodrahalli, Xuezhi Wang, Pidong Wang, ZiRui Wang, Tao Wang, John Wieting, Yuhuai Wu, Kelvin Xu, Yunhan Xu, Linting Xue, Pengcheng Yin, Jiahui Yu, Qiao Zhang, Steven Zheng, Ce Zheng, Weikang Zhou, Denny Zhou, Slav Petrov, Yonghui Wu

Through extensive evaluations on English and multilingual language, and reasoning tasks, we demonstrate that PaLM 2 has significantly improved quality on downstream tasks across different model sizes, while simultaneously exhibiting faster and more efficient inference compared to PaLM.

 Ranked #1 on Question Answering on TriviaQA (using extra training data)

Language Modelling Question Answering

Towards Generalizable Reinforcement Learning for Trade Execution

no code implementations12 May 2023 Chuheng Zhang, Yitong Duan, Xiaoyu Chen, Jianyu Chen, Jian Li, Li Zhao

To evaluate our algorithms, we also implement a carefully designed simulator based on historical limit order book (LOB) data to provide a high-fidelity benchmark for different algorithms.

Offline RL reinforcement-learning +1

MolKD: Distilling Cross-Modal Knowledge in Chemical Reactions for Molecular Property Prediction

no code implementations3 May 2023 Liang Zeng, Lanqing Li, Jian Li

This paper studies this problem and proposes to incorporate chemical domain knowledge, specifically related to chemical reactions, for learning effective molecular representations.

Drug Discovery Molecular Property Prediction +1

Robust Neural Architecture Search

no code implementations6 Apr 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Neural Architectures Search (NAS) becomes more and more popular over these years.

Image Classification Neural Architecture Search

Joint cortical registration of geometry and function using semi-supervised learning

no code implementations2 Mar 2023 Jian Li, Greta Tuckute, Evelina Fedorenko, Brian L. Edlow, Bruce Fischl, Adrian V. Dalca

Brain surface-based image registration, an important component of brain image analysis, establishes spatial correspondence between cortical surfaces.

Image Registration

Information extraction and artwork pricing

no code implementations16 Feb 2023 Jaehyuk Choi, Lan Ju, Jian Li, Zhiyong Tu

Traditional art pricing models often lack fine measurements of painting content.

Learning with Noisy labels via Self-supervised Adversarial Noisy Masking

no code implementations CVPR 2023 Yuanpeng Tu, Boshen Zhang, Yuxi Li, Liang Liu, Jian Li, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Cai Rong Zhao

Collecting large-scale datasets is crucial for training deep models, annotating the data, however, inevitably yields noisy labels, which poses challenges to deep learning algorithms.

Ranked #2 on Image Classification on Clothing1M (using extra training data)

Learning with noisy labels

Operation-level Progressive Differentiable Architecture Search

1 code implementation11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

It can effectively alleviate the unfair competition between operations during the search phase of DARTS by offsetting the inherent unfair advantage of the skip connection over other operations.

Neural Architecture Search

Improving Differentiable Architecture Search via Self-Distillation

no code implementations11 Feb 2023 Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Differentiable Architecture Search (DARTS) is a simple yet efficient Neural Architecture Search (NAS) method.

Neural Architecture Search

Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search

no code implementations2 Feb 2023 Clemens JS Schaefer, Elfie Guo, Caitlin Stanton, Xiaofan Zhang, Tom Jablin, Navid Lambert-Shirzad, Jian Li, Chiachen Chou, Siddharth Joshi, Yu Emma Wang

In this paper, we propose a method to efficiently determine quantization configurations of different tensors in ML models using post-training mixed precision quantization.


Rethinking Mobile Block for Efficient Attention-based Models

1 code implementation ICCV 2023 Jiangning Zhang, Xiangtai Li, Jian Li, Liang Liu, Zhucun Xue, Boshen Zhang, Zhengkai Jiang, Tianxin Huang, Yabiao Wang, Chengjie Wang

This paper focuses on developing modern, efficient, lightweight models for dense predictions while trading off parameters, FLOPs, and performance.


FCC: Feature Clusters Compression for Long-Tailed Visual Recognition

1 code implementation CVPR 2023 Jian Li, Ziyao Meng, Daqian Shi, Rui Song, Xiaolei Diao, Jingwen Wang, Hao Xu

Through representation learning, DNNs can map BFs into dense clusters in feature space, while the features of minority classes often show sparse clusters.

Representation Learning

Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits

no code implementations12 Dec 2022 Guojun Xiong, Jian Li

Most research for this problem focuses exclusively on the settings that players have \textit{full access} to all arms and receive no reward when pulling the same arm.

Decision Making Distributed Optimization

Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models

no code implementations1 Dec 2022 Qiong Wu, Jian Li, Zhenming Liu, Yanhua Li, Mihai Cucuringu

This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or interactions between users in a social network.

Ensemble Learning Time Series Analysis

OpenFE: Automated Feature Generation with Expert-level Performance

2 code implementations22 Nov 2022 Tianping Zhang, Zheyu Zhang, Zhiyuan Fan, Haoyan Luo, Fengyuan Liu, Qian Liu, Wei Cao, Jian Li

In the two competitions, features generated by OpenFE with a simple baseline model can beat 99. 3% and 99. 6% data science teams respectively.

Feature Importance

Knowledge-Guided Exploration in Deep Reinforcement Learning

no code implementations26 Oct 2022 Sahisnu Mazumder, Bing Liu, Shuai Wang, Yingxuan Zhu, Xiaotian Yin, Lifeng Liu, Jian Li

This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP).

reinforcement-learning Reinforcement Learning (RL)

Decomposing User-APP Graph into Subgraphs for Effective APP and User Embedding Learning

no code implementations13 Oct 2022 Tan Yu, Jun Zhi, Yufei Zhang, Jian Li, Hongliang Fei, Ping Li

In this paper, we formulate the APP-installation user embedding learning into a bipartite graph embedding problem.

Graph Embedding Graph Learning

DIGAT: Modeling News Recommendation with Dual-Graph Interaction

1 code implementation11 Oct 2022 Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, Kam-Fai Wong

Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal.

Graph Attention News Recommendation +1

MetaTrader: An Reinforcement Learning Approach Integrating Diverse Policies for Portfolio Optimization

no code implementations1 Sep 2022 Hui Niu, Siyuan Li, Jian Li

We evaluate the proposed approach on three real-world index datasets and compare it to state-of-the-art baselines.

Imitation Learning Management +3

Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization

no code implementations22 Aug 2022 Zhize Li, Jian Li

We provide a clean and tight analysis of ProxSVRG+, which shows that it outperforms the deterministic proximal gradient descent (ProxGD) for a wide range of minibatch sizes, hence solves an open problem proposed in Reddi et al. (2016b).

Waveform Design for Mutual Interference Mitigation in Automotive Radar

no code implementations8 Aug 2022 Arindam Bose, Bo Tang, Wenjie Huang, Mojtaba Soltanalian, Jian Li

The mutual interference between similar radar systems can result in reduced radar sensitivity and increased false alarm rates.

Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability

no code implementations26 Jul 2022 Zhouzi Li, Zixuan Wang, Jian Li

Based on this empirical observation, we attempt to theoretically and empirically explain the dynamics of various key quantities that lead to the change of sharpness in each phase of EOS.

Efficient Algorithms for Sparse Moment Problems without Separation

no code implementations26 Jul 2022 Zhiyuan Fan, Jian Li

Our algorithm for the one-dimensional problem (also called the sparse Hausdorff moment problem) is a robust version of the classic Prony's method, and our contribution mainly lies in the analysis.

Topic Models

Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning

no code implementations21 Jul 2022 Gaurav Bagwe, Jian Li, Xiaoyong Yuan, Lan Zhang

Moreover, to improve data efficiency and provide better generalization performance, we train the policy model with augmented data (e. g., noisy BSM and noisy surveillance images).

Autonomous Driving reinforcement-learning +1

Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation

2 code implementations6 Jun 2022 Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li

While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-level loops with maximization-based decoding algorithms (\textit{e. g.}, greedy search).

Text Generation Text Summarization

Uncertainty quantification of two-phase flow in porous media via coupled-TgNN surrogate model

no code implementations28 May 2022 Jian Li, Dongxiao Zhang, Tianhao He, Qiang Zheng

In this work, a novel coupled theory-guided neural network (TgNN) based surrogate model is built to facilitate computation efficiency under the premise of satisfactory accuracy.

Generalization Bounds for Gradient Methods via Discrete and Continuous Prior

no code implementations27 May 2022 Xuanyuan Luo, Luo Bei, Jian Li

In this paper, we introduce a new discrete data-dependent prior to the PAC-Bayesian framework, and prove a high probability generalization bound of order $O(\frac{1}{n}\cdot \sum_{t=1}^T(\gamma_t/\varepsilon_t)^2\left\|{\mathbf{g}_t}\right\|^2)$ for Floored GD (i. e. a version of gradient descent with precision level $\varepsilon_t$), where $n$ is the number of training samples, $\gamma_t$ is the learning rate at step $t$, $\mathbf{g}_t$ is roughly the difference of the gradient computed using all samples and that using only prior samples.

Generalization Bounds Learning Theory

ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification

no code implementations23 May 2022 Liang Zeng, Lanqing Li, Ziqi Gao, Peilin Zhao, Jian Li

Motivated by this observation, we propose a principled GCL framework on Imbalanced node classification (ImGCL), which automatically and adaptively balances the representations learned from GCL without labels.

Classification Contrastive Learning +2

Ridgeless Regression with Random Features

1 code implementation1 May 2022 Jian Li, Yong liu, Yingying Zhang

Recent theoretical studies illustrated that kernel ridgeless regression can guarantee good generalization ability without an explicit regularization.


Sharper Utility Bounds for Differentially Private Models

no code implementations22 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

In this paper, by introducing Generalized Bernstein condition, we propose the first $\mathcal{O}\big(\frac{\sqrt{p}}{n\epsilon}\big)$ high probability excess population risk bound for differentially private algorithms under the assumptions $G$-Lipschitz, $L$-smooth, and Polyak-{\L}ojasiewicz condition, based on gradient perturbation method.

Stability and Generalization of Differentially Private Minimax Problems

no code implementations11 Apr 2022 Yilin Kang, Yong liu, Jian Li, Weiping Wang

To the best of our knowledge, this is the first time to analyze the generalization performance of general minimax paradigm, taking differential privacy into account.

Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation

no code implementations26 Feb 2022 Guojun Xiong, Shufan Wang, Jian Li, Rahul Singh

Using this structural result, we establish the indexability of our problem, and employ the Whittle index policy to minimize average latency.

Edge-computing Q-Learning +1

ASFD: Automatic and Scalable Face Detector

no code implementations26 Jan 2022 Jian Li, Bin Zhang, Yabiao Wang, Ying Tai, Zhenyu Zhang, Chengjie Wang, Jilin Li, Xiaoming Huang, Yili Xia

Along with current multi-scale based detectors, Feature Aggregation and Enhancement (FAE) modules have shown superior performance gains for cutting-edge object detection.

Face Detection object-detection +1

Machine learning prediction for mean motion resonance behaviour -- The planar case

no code implementations18 Jan 2022 Xin Li, Jian Li, Zhihong Jeff Xia, Nikolaos Georgakarakos

Most recently, machine learning has been used to study the dynamics of integrable Hamiltonian systems and the chaotic 3-body problem.

BIG-bench Machine Learning Numerical Integration

SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-Resolution

no code implementations12 Jan 2022 Jiangning Zhang, Chao Xu, Jian Li, Yue Han, Yabiao Wang, Ying Tai, Yong liu

In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device.

Colorization Image Colorization +1

Convolution of Convolution: Let Kernels Spatially Collaborate

1 code implementation CVPR 2022 Rongzhen Zhao, Jian Li, Zhenzhi Wu

In the biological visual pathway, especially the retina, neurons are tiled along spatial dimensions with the electrical coupling as their local association, while in a convolution layer, kernels are placed along the channel dimension singly.

DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities

no code implementations15 Dec 2021 Shuo Sun, Wanqi Xue, Rundong Wang, Xu He, Junlei Zhu, Jian Li, Bo An

Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading.

Algorithmic Trading Decision Making +3

AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020

1 code implementation25 Nov 2021 Jin Xu, Mingjian Chen, Jianqiang Huang, Xingyuan Tang, Ke Hu, Jian Li, Jia Cheng, Jun Lei

Graph Neural Networks (GNNs) have become increasingly popular and achieved impressive results in many graph-based applications.

Graph Classification Node Classification

ML-EXray: Visibility into ML Deployment on the Edge

no code implementations8 Nov 2021 Hang Qiu, Ioanna Vavelidou, Jian Li, Evgenya Pergament, Pete Warden, Sandeep Chinchali, Zain Asgar, Sachin Katti

The key challenge is that there is not much visibility into ML inference execution on edge devices, and very little awareness of potential issues during the edge deployment process.


Critical Learning Periods in Federated Learning

no code implementations12 Sep 2021 Gang Yan, Hao Wang, Jian Li

In this work, we show that the final test accuracy of FL is dramatically affected by the early phase of the training process, i. e., FL exhibits critical learning periods, in which small gradient errors can have irrecoverable impact on the final test accuracy.

Federated Learning Test

Unsupervised Open-Domain Question Answering

no code implementations31 Aug 2021 Pengfei Zhu, Xiaoguang Li, Jian Li, Hai Zhao

Open-domain Question Answering (ODQA) has achieved significant results in terms of supervised learning manner.

Machine Reading Comprehension Open-Domain Question Answering

Analyzing and Mitigating Interference in Neural Architecture Search

no code implementations29 Aug 2021 Jin Xu, Xu Tan, Kaitao Song, Renqian Luo, Yichong Leng, Tao Qin, Tie-Yan Liu, Jian Li

In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe: 1) the interference on a shared operator between two child models is positively correlated with the number of different operators; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar.

Neural Architecture Search Reading Comprehension

Accelerating Serverless Computing by Harvesting Idle Resources

no code implementations28 Aug 2021 Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, Seung-Jong Park

Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions.

Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling

no code implementations26 Jul 2021 Liang Zeng, Lei Wang, Hui Niu, Ruchen Zhang, Ling Wang, Jian Li

In a set of experiments on three real-world financial markets: stocks, cryptocurrencies, and ETFs, LARA significantly outperforms several machine learning based methods on the Qlib quantitative investment platform.

Metric Learning Time Series Analysis

Discrete Auto-regressive Variational Attention Models for Text Modeling

1 code implementation16 Jun 2021 Xianghong Fang, Haoli Bai, Jian Li, Zenglin Xu, Michael Lyu, Irwin King

We further design discrete latent space for the variational attention and mathematically show that our model is free from posterior collapse.

Language Modelling

Simple Combinatorial Algorithms for Combinatorial Bandits: Corruptions and Approximations

no code implementations12 Jun 2021 Haike Xu, Jian Li

Our algorithm achieves an (approximation) regret bound of $\tilde{O}\left(d\sqrt{KT}\right)$.

AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange

no code implementations10 Jun 2021 Liang Zeng, Jin Xu, Zijun Yao, Yanqiao Zhu, Jian Li

In this paper, we propose to substitute these redundant channels with other informative channels to achieve this goal.

Graph Classification Graph Learning +4

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

1 code implementation NeurIPS 2021 Jiangning Zhang, Chao Xu, Jian Li, Wenzhou Chen, Yabiao Wang, Ying Tai, Shuo Chen, Chengjie Wang, Feiyue Huang, Yong liu

Inspired by biological evolution, we explain the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derive that both of them have consistent mathematical representation.

Image Retrieval Retrieval

Towards Sharper Utility Bounds for Differentially Private Pairwise Learning

no code implementations7 May 2021 Yilin Kang, Yong liu, Jian Li, Weiping Wang

Pairwise learning focuses on learning tasks with pairwise loss functions, depends on pairs of training instances, and naturally fits for modeling relationships between pairs of samples.

Weighted SPICE Algorithms for Range-Doppler Imaging Using One-Bit Automotive Radar

no code implementations31 Mar 2021 Xiaolei Shang, Jian Li, Petre Stoica

The recently proposed hyperparameter-free (and hence user friendly) weighted SPICE algorithms, including SPICE, LIKES, SLIM and IAA, achieve excellent parameter estimation performance for data sampled with high precision.

Sinusoidal Parameter Estimation from Signed Measurements via Majorization-Minimization Based RELAX

no code implementations21 Mar 2021 Jiaying Ren, Tianyi Zhang, Jian Li, Petre Stoica

In a previous paper, a relaxation-based algorithm, referred to as 1bRELAX, has been proposed to iteratively maximize the likelihood function.

Joint RFI Mitigation and Radar Echo Recovery for One-Bit UWB Radar

no code implementations19 Mar 2021 Tianyi Zhang, Jiaying Ren, Jian Li, Lam H. Nguyen, Petre Stoica

Radio frequency interference (RFI) mitigation and radar echo recovery are critically important for the proper functioning of ultra-wideband (UWB) radar systems using one-bit sampling techniques.

Both qubits of the singlet state can be steered simultaneously by multiple independent observers via sequential measurement

no code implementations24 Feb 2021 Kun Liu, Tongjun Liu, Wei Fang, Jian Li, Qin Wang

Quantum correlation is a fundamental property which distinguishes quantum systems from classical ones, and it is also a fragile resource under projective measurement.

Quantum Physics

Return-Based Contrastive Representation Learning for Reinforcement Learning

no code implementations ICLR 2021 Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu

Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL).

Atari Games reinforcement-learning +2

RFI Mitigation for One-bit UWB Radar Systems

no code implementations17 Feb 2021 Tianyi Zhang, Jiaying Ren, Jian Li, Lam H. Nguyen, Petre Stoica

A one-bit UWB system obtains its signed measurements via a low-cost and high rate sampling scheme, referred to as the Continuous Time Binary Value (CTBV) technology.


Straggler-Resilient Distributed Machine Learning with Dynamic Backup Workers

no code implementations11 Feb 2021 Guojun Xiong, Gang Yan, Rahul Singh, Jian Li

In this paradigm, each worker maintains a local estimate of the optimal parameter vector, and iteratively updates it by waiting and averaging all estimates obtained from its neighbors, and then corrects it on the basis of its local dataset.

BIG-bench Machine Learning Distributed Optimization

Investigating the nature of MGRO J1908+06 with multiwavelength observations

no code implementations10 Feb 2021 Jian Li, Ruo-Yu Liu, Emma de Ona Wilhelmi, Diego F. Torres, Qian-Cheng Liu, Matthew Kerr, Rolf Buehler, Yang Su, Hao-Ning He, Meng-Yuan Xiao

The unidentified TeV source MGRO J1908+06, with emission extending from hundreds of GeV to beyond 100TeV, is one of the most intriguing sources in the Galactic plane.

High Energy Astrophysical Phenomena

Observation of ultra-slow shock waves in a tunable magnetic lattice

no code implementations28 Jan 2021 Jian Li, Chockalingam Senthilnathan, Tal Cohen

The combination of fast propagation speeds and highly localized nature has hindered the direct observation of the evolution of shock waves at the molecular scale.

Soft Condensed Matter

On the quantization of recurrent neural networks

no code implementations14 Jan 2021 Jian Li, Raziel Alvarez

Integer quantization of neural networks can be defined as the approximation of the high precision computation of the canonical neural network formulation, using reduced integer precision.


Learning Augmented Index Policy for Optimal Service Placement at the Network Edge

no code implementations10 Jan 2021 Guojun Xiong, Rahul Singh, Jian Li

We pose the problem as a Markov decision process (MDP) in which the system state is given by describing, for each service, the number of customers that are currently waiting at the edge to obtain the service.


Theory of polymer diffusion in polymer-nanoparticle mixtures: effect of nanoparticle concentration and polymer length

no code implementations22 Nov 2020 Bokai Zhang, Jian Li, Juan-mei Hu, Lei Liu

The dynamics of polymer-nanoparticle (NP) mixtures, which involves multiple scales and system-specific variables, has posed a long-standing challenge on its theoretical description.

Soft Condensed Matter

Distributed Stochastic Consensus Optimization with Momentum for Nonconvex Nonsmooth Problems

no code implementations10 Nov 2020 Zhiguo Wang, Jiawei Zhang, Tsung-Hui Chang, Jian Li, Zhi-Quan Luo

While many distributed optimization algorithms have been proposed for solving smooth or convex problems over the networks, few of them can handle non-convex and non-smooth problems.

Distributed Optimization

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.

BIG-bench Machine Learning feature selection

Kalman Filtering Attention for User Behavior Modeling in CTR Prediction

no code implementations NeurIPS 2020 Hu Liu, Jing Lu, Xiwei Zhao, Sulong Xu, Hao Peng, Yutong Liu, Zehua Zhang, Jian Li, Junsheng Jin, Yongjun Bao, Weipeng Yan

First, conventional attentions mostly limit the attention field only to a single user's behaviors, which is not suitable in e-commerce where users often hunt for new demands that are irrelevant to any historical behaviors.

Click-Through Rate Prediction

Loosely Coupled Federated Learning Over Generative Models

no code implementations28 Sep 2020 Shaoming Song, Yunfeng Shao, Jian Li

This paper proposes Loosely Coupled Federated Learning (LC-FL), a framework using generative models as transmission media to achieve low communication cost and heterogeneous federated learning.

BIG-bench Machine Learning Federated Learning

Secure Transmission by Leveraging Multiple Intelligent Reflecting Surfaces in MISO Systems

no code implementations9 Aug 2020 Jian Li, Lan Zhang, Kaiping Xue, Yuguang Fang

Specifically, to guarantee the worst-case achievable secrecy rate among multiple legitimate users, we formulate a max-min problem that can be solved by an alternative optimization method to decouple it into multiple sub-problems.

LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition

no code implementations9 Aug 2020 Jin Xu, Xu Tan, Yi Ren, Tao Qin, Jian Li, Sheng Zhao, Tie-Yan Liu

However, there are more than 6, 000 languages in the world and most languages are lack of speech training data, which poses significant challenges when building TTS and ASR systems for extremely low-resource languages.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

ACFD: Asymmetric Cartoon Face Detector

2 code implementations2 Jul 2020 Bin Zhang, Jian Li, Yabiao Wang, Zhipeng Cui, Yili Xia, Chengjie Wang, Jilin Li, Feiyue Huang

Cartoon face detection is a more challenging task than human face detection due to many difficult scenarios is involved.

Binary Classification Face Detection

Neural Architecture Optimization with Graph VAE

no code implementations18 Jun 2020 Jian Li, Yong liu, Jiankun Liu, Weiping Wang

The encoder and the decoder belong to a graph VAE, mapping architectures between continuous representations and network architectures.

Neural Architecture Search

Exploration by Maximizing Rényi Entropy for Reward-Free RL Framework

no code implementations11 Jun 2020 Chuheng Zhang, Yuanying Cai, Longbo Huang, Jian Li

In the planning phase, the agent computes a good policy for any reward function based on the dataset without further interacting with the environment.

Q-Learning Reinforcement Learning (RL)

Improved Algorithms for Convex-Concave Minimax Optimization

no code implementations NeurIPS 2020 Yuanhao Wang, Jian Li

This paper studies minimax optimization problems $\min_x \max_y f(x, y)$, where $f(x, y)$ is $m_x$-strongly convex with respect to $x$, $m_y$-strongly concave with respect to $y$ and $(L_x, L_{xy}, L_y)$-smooth.

ASFD: Automatic and Scalable Face Detector

no code implementations25 Mar 2020 Bin Zhang, Jian Li, Yabiao Wang, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Yili Xia, Wenjiang Pei, Rongrong Ji

In this paper, we propose a novel Automatic and Scalable Face Detector (ASFD), which is based on a combination of neural architecture search techniques as well as a new loss design.

Neural Architecture Search

Meta-Embeddings Based On Self-Attention

no code implementations3 Mar 2020 Qichen Li, Yuanqing Lin, Luofeng Zhou, Jian Li

Creating meta-embeddings for better performance in language modelling has received attention lately, and methods based on concatenation or merely calculating the arithmetic mean of more than one separately trained embeddings to perform meta-embeddings have shown to be beneficial.

Language Modelling Machine Translation +3

Convolutional Spectral Kernel Learning

no code implementations28 Feb 2020 Jian Li, Yong liu, Weiping Wang

Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics.

PA-Cache: Evolving Learning-Based Popularity-Aware Content Caching in Edge Networks

no code implementations20 Feb 2020 Qilin Fan, Xiuhua Li, Jian Li, Qiang He, Kai Wang, Junhao Wen

Compared to the conventional content delivery networks, caches in edge networks with smaller sizes usually have to accommodate more bursty requests.

Decision Making

Data Heterogeneity Differential Privacy: From Theory to Algorithm

no code implementations20 Feb 2020 Yilin Kang, Jian Li, Yong liu, Weiping Wang

Traditionally, the random noise is equally injected when training with different data instances in the field of differential privacy (DP).

BIG-bench Machine Learning

Online Algorithms for Multi-shop Ski Rental with Machine Learned Advice

1 code implementation NeurIPS 2020 Shufan Wang, Jian Li, Shiqiang Wang

We obtain both deterministic and randomized online algorithms with provably improved performance when either a single or multiple ML predictions are used to make decisions.

Decision Making

Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web

3 code implementations16 Jan 2020 Silei Xu, Giovanni Campagna, Jian Li, Monica S. Lam

The key concept is to cover the space of possible compound queries on the database with a large number of in-domain questions synthesized with the help of a corpus of generic query templates.

Question Answering Semantic Parsing +1

Neuron Interaction Based Representation Composition for Neural Machine Translation

no code implementations22 Nov 2019 Jian Li, Xing Wang, Baosong Yang, Shuming Shi, Michael R. Lyu, Zhaopeng Tu

Starting from this intuition, we propose a novel approach to compose representations learned by different components in neural machine translation (e. g., multi-layer networks or multi-head attention), based on modeling strong interactions among neurons in the representation vectors.

Machine Translation Translation

Fast Learning of Temporal Action Proposal via Dense Boundary Generator

3 code implementations11 Nov 2019 Chuming Lin, Jian Li, Yabiao Wang, Ying Tai, Donghao Luo, Zhipeng Cui, Chengjie Wang, Jilin Li, Feiyue Huang, Rongrong Ji

In this paper, we propose an efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.

General Classification Optical Flow Estimation +2

Metric Classification Network in Actual Face Recognition Scene

no code implementations25 Oct 2019 Jian Li, Yan Wang, Xiubao Zhang, Weihong Deng, Haifeng Shen

In this paper, we train a validation classifier to normalize the decision threshold, which means that the result can be obtained directly without replacing the threshold.

Classification Face Recognition +3

Optimizing Speech Recognition For The Edge

no code implementations26 Sep 2019 Yuan Shangguan, Jian Li, Qiao Liang, Raziel Alvarez, Ian McGraw

While most deployed speech recognition systems today still run on servers, we are in the midst of a transition towards deployments on edge devices.

Efficient Neural Network Quantization +2

Semi-supervised Vector-valued Learning: Improved Bounds and Algorithms

1 code implementation11 Sep 2019 Jian Li, Yong liu, Weiping Wang

Vector-valued learning, where the output space admits a vector-valued structure, is an important problem that covers a broad family of important domains, e. g. multi-task learning and transfer learning.

Multi-class Classification Multi-Label Learning +1

Automated Spectral Kernel Learning

1 code implementation11 Sep 2019 Jian Li, Yong liu, Weiping Wang

The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks.

Learning Guided Convolutional Network for Depth Completion

2 code implementations3 Aug 2019 Jie Tang, Fei-Peng Tian, Wei Feng, Jian Li, Ping Tan

It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion.

Autonomous Driving Depth Completion +1

NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization

1 code implementation26 Jun 2019 Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang, Jie Tang

Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.

Network Embedding

AddGraph_ Anomaly Detection in Dynamic Graph Using Attention-based Temporal GCN

no code implementations (IJCAI 2019 Li Zheng, Zhenpeng Li, Jian Li, Zhao Li, and Jun Gao

Anomaly detection in dynamic graphs becomes very critical in many different application scenarios, e. g., recommender systems, while it also raises huge challenges due to the high flexible nature of anomaly and lack of sufficient labelled data.

Anomaly Detection Edge Detection +1

Gradient Descent Maximizes the Margin of Homogeneous Neural Networks

1 code implementation ICLR 2020 Kaifeng Lyu, Jian Li

In this paper, we study the implicit regularization of the gradient descent algorithm in homogeneous neural networks, including fully-connected and convolutional neural networks with ReLU or LeakyReLU activations.

Towards Sharp Analysis for Distributed Learning with Random Features

1 code implementation7 Jun 2019 Jian Li, Yong liu, Weiping Wang

In this paper, using refined proof techniques, we first extend the optimal rates for distributed learning with random features to the non-attainable case.

Relation Extraction with Temporal Reasoning Based on Memory Augmented Distant Supervision

1 code implementation NAACL 2019 Jianhao Yan, Lin He, Ruqin Huang, Jian Li, Ying Liu

This paper formulates the problem of relation extraction with temporal reasoning and proposes a solution to predict whether two given entities participate in a relation at a given time spot.

Relation Extraction valid

Policy Search by Target Distribution Learning for Continuous Control

no code implementations27 May 2019 Chuheng Zhang, Yuanqi Li, Jian Li

We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process.

Continuous Control Policy Gradient Methods +1

Robust Variational Autoencoder

no code implementations23 May 2019 Haleh Akrami, Anand A. Joshi, Jian Li, Sergul Aydore, Richard M. Leahy

Machine learning methods often need a large amount of labeled training data.

Outlier Detection

Anti-Confusing: Region-Aware Network for Human Pose Estimation

no code implementations3 May 2019 Xuan Cao, Yanhao Ge, Ying Tai, Wei zhang, Jian Li, Chengjie Wang, Jilin Li, Feiyue Huang

In this work, we propose a novel framework named Region-Aware Network (RANet), which learns the ability of anti-confusing in case of heavy occlusion, nearby person and symmetric appearance, for human pose estimation.

Data Augmentation Pose Estimation

Automatic Target Recognition Using Discrimination Based on Optimal Transport

no code implementations6 Apr 2019 Ali Sadeghian, Deoksu Lim, Johan Karlsson, Jian Li

The use of distances based on optimal transportation has recently shown promise for discrimination of power spectra.

Information Aggregation for Multi-Head Attention with Routing-by-Agreement

no code implementations NAACL 2019 Jian Li, Baosong Yang, Zi-Yi Dou, Xing Wang, Michael R. Lyu, Zhaopeng Tu

Multi-head attention is appealing for its ability to jointly extract different types of information from multiple representation subspaces.

Machine Translation Translation

Context-Aware Self-Attention Networks

no code implementations15 Feb 2019 Baosong Yang, Jian Li, Derek Wong, Lidia S. Chao, Xing Wang, Zhaopeng Tu

Self-attention model have shown its flexibility in parallel computation and the effectiveness on modeling both long- and short-term dependencies.


Efficient Cross-Validation for Semi-Supervised Learning

no code implementations13 Feb 2019 Yong Liu, Jian Li, Guangjun Wu, Lizhong Ding, Weiping Wang

In this paper, we provide a method to approximate the CV for manifold regularization based on a notion of robust statistics, called Bouligand influence function (BIF).

Model Selection

Max-Diversity Distributed Learning: Theory and Algorithms

no code implementations19 Dec 2018 Yong Liu, Jian Li, Weiping Wang

We study the risk performance of distributed learning for the regularization empirical risk minimization with fast convergence rate, substantially improving the error analysis of the existing divide-and-conquer based distributed learning.

Learning Theory

Learning Features of Network Structures Using Graphlets

no code implementations13 Dec 2018 Kun Tu, Jian Li, Don Towsley, Dave Braines, Liam Turner

In this paper, we explore the role of \emph{graphlets} in network classification for both static and temporal networks.

General Classification Learning Network Representations +1

Multi-Class Learning: From Theory to Algorithm

no code implementations NeurIPS 2018 Jian Li, Yong liu, Rong Yin, Hua Zhang, Lizhong Ding, Weiping Wang

In this paper, we study the generalization performance of multi-class classification and obtain a shaper data-dependent generalization error bound with fast convergence rate, substantially improving the state-of-art bounds in the existing data-dependent generalization analysis.

Classification General Classification +1

DSFD: Dual Shot Face Detector

3 code implementations CVPR 2019 Jian Li, Yabiao Wang, Changan Wang, Ying Tai, Jianjun Qian, Jian Yang, Chengjie Wang, Jilin Li, Feiyue Huang

In this paper, we propose a novel face detection network with three novel contributions that address three key aspects of face detection, including better feature learning, progressive loss design and anchor assign based data augmentation, respectively.

Data Augmentation Face Detection

Multi-Head Attention with Disagreement Regularization

no code implementations EMNLP 2018 Jian Li, Zhaopeng Tu, Baosong Yang, Michael R. Lyu, Tong Zhang

Multi-head attention is appealing for the ability to jointly attend to information from different representation subspaces at different positions.


Guided Exploration in Deep Reinforcement Learning

no code implementations27 Sep 2018 Sahisnu Mazumder, Bing Liu, Shuai Wang, Yingxuan Zhu, Xiaotian Yin, Lifeng Liu, Jian Li, Yongbing Huang

This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of \textit{state-action permissibility} (SAP).

reinforcement-learning Reinforcement Learning (RL)

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

1 code implementation CVPR 2019 Zhen He, Jian Li, Daxue Liu, Hangen He, David Barber

To achieve both label-free and end-to-end learning of MOT, we propose a Tracking-by-Animation framework, where a differentiable neural model first tracks objects from input frames and then animates these objects into reconstructed frames.

Multi-Object Tracking Online Multi-Object Tracking

A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization

no code implementations7 Sep 2018 Zhize Li, Jian Li

Besides, if the hyperparameters (e. g., the Lipschitz smooth parameter $L$) are not available, we propose a guessing algorithm for guessing them dynamically and also prove a similar convergence rate.

Network Classification in Temporal Networks Using Motifs

no code implementations10 Jul 2018 Kun Tu, Jian Li, Don Towsley, Dave Braines, Liam D. Turner

Network classification has a variety of applications, such as detecting communities within networks and finding similarities between those representing different aspects of the real world.

Classification General Classification

Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference

no code implementations29 Mar 2018 Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu, Jian Li

In this paper, we apply the variance reduction tricks on Hamiltonian Monte Carlo and achieve better theoretical convergence results compared with the variance-reduced Langevin dynamics.

Bayesian Inference

Gradient Boosting With Piece-Wise Linear Regression Trees

1 code implementation15 Feb 2018 Yu Shi, Jian Li, Zhize Li

We show that PL Trees can accelerate convergence of GBDT and improve the accuracy.

Ensemble Learning regression

A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization

no code implementations NeurIPS 2018 Zhize Li, Jian Li

In particular, ProxSVRG+ generalizes the best results given by the SCSG algorithm, recently proposed by [Lei et al., 2017] for the smooth nonconvex case.

Code Completion with Neural Attention and Pointer Networks

1 code implementation27 Nov 2017 Jian Li, Yue Wang, Michael R. Lyu, Irwin King

Intelligent code completion has become an essential research task to accelerate modern software development.

Code Completion

Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec

4 code implementations9 Oct 2017 Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang

This work lays the theoretical foundation for skip-gram based network embedding methods, leading to a better understanding of latent network representation learning.

Network Embedding

Generative Adversarial Mapping Networks

no code implementations28 Sep 2017 Jianbo Guo, Guangxiang Zhu, Jian Li

They fit generative models by minimizing certain distance measure between the real image distribution and the generated data distribution.

Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration

no code implementations4 Jun 2017 Lijie Chen, Anupam Gupta, Jian Li, Mingda Qiao, Ruosong Wang

We provide a novel instance-wise lower bound for the sample complexity of the problem, as well as a nontrivial sampling algorithm, matching the lower bound up to a factor of $\ln|\mathcal{F}|$.

Multi-Armed Bandits

SVM via Saddle Point Optimization: New Bounds and Distributed Algorithms

no code implementations20 May 2017 Yifei Jin, Lingxiao Huang, Jian Li

Our algorithms achieve $(1-\epsilon)$-approximations with running time $\tilde{O}(nd+n\sqrt{d / \epsilon})$ for both variants, where $n$ is the number of points and $d$ is the dimensionality.

Practical Algorithms for Best-K Identification in Multi-Armed Bandits

no code implementations19 May 2017 Haotian Jiang, Jian Li, Mingda Qiao

In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions.

Multi-Armed Bandits

Single-Pass PCA of Large High-Dimensional Data

no code implementations25 Apr 2017 Wenjian Yu, Yu Gu, Jian Li, Shenghua Liu, Yaohang Li

Principal component analysis (PCA) is a fundamental dimension reduction tool in statistics and machine learning.

Dimensionality Reduction Vocal Bursts Intensity Prediction

Learning Gradient Descent: Better Generalization and Longer Horizons

2 code implementations ICML 2017 Kaifeng Lv, Shunhua Jiang, Jian Li

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters.


Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection

no code implementations13 Feb 2017 Lijie Chen, Jian Li, Mingda Qiao

In the Best-$k$-Arm problem, we are given $n$ stochastic bandit arms, each associated with an unknown reward distribution.

Generalized Haar Filter based Deep Networks for Real-Time Object Detection in Traffic Scene

no code implementations30 Oct 2016 Keyu Lu, Jian Li, Xiangjing An, Hangen He

This paper presents a generalized Haar filter based deep network which is suitable for the object detection tasks in traffic scene.

object-detection Real-Time Object Detection +1

Optimal In-Place Suffix Sorting

2 code implementations26 Oct 2016 Zhize Li, Jian Li, Hongwei Huo

The open problem asked to design in-place algorithms in $o(n\log n)$ time and ultimately, in $O(n)$ time for (read-only) integer alphabets with $|\Sigma| \leq n$.

Data Structures and Algorithms

Combinatorial Multi-Armed Bandit with General Reward Functions

no code implementations NeurIPS 2016 Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu

Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.

Towards Instance Optimal Bounds for Best Arm Identification

no code implementations22 Aug 2016 Lijie Chen, Jian Li, Mingda Qiao

$H(I)=\sum_{i=2}^n\Delta_{[i]}^{-2}$ is the complexity of the instance.

Characterizing Driving Styles with Deep Learning

1 code implementation13 Jul 2016 Weishan Dong, Jian Li, Renjie Yao, Changsheng Li, Ting Yuan, Lanjun Wang

Characterizing driving styles of human drivers using vehicle sensor data, e. g., GPS, is an interesting research problem and an important real-world requirement from automotive industries.

Autonomous Driving Driver Identification

Store Location Selection via Mining Search Query Logs of Baidu Maps

no code implementations12 Jun 2016 Mengwen Xu, Tianyi Wang, Zhengwei Wu, Jingbo Zhou, Jian Li, Haishan Wu

In this paper, we propose a Demand Distribution Driven Store Placement (D3SP) framework for business store placement by mining search query data from Baidu Maps.


Open Problem: Best Arm Identification: Almost Instance-Wise Optimality and the Gap Entropy Conjecture

no code implementations27 May 2016 Lijie Chen, Jian Li

The best arm identification problem (BEST-1-ARM) is the most basic pure exploration problem in stochastic multi-armed bandits.

Multi-Armed Bandits

Pure Exploration of Multi-armed Bandit Under Matroid Constraints

no code implementations23 May 2016 Lijie Chen, Anupam Gupta, Jian Li

In a Best-Basis instance, we are given $n$ stochastic arms with unknown reward distributions, as well as a matroid $\mathcal{M}$ over the arms.

On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs

no code implementations NeurIPS 2015 Wei Cao, Jian Li, Yufei Tao, Zhize Li

This paper discusses how to efficiently choose from $n$ unknowndistributions the $k$ ones whose means are the greatest by a certainmetric, up to a small relative error.

Multi-Armed Bandits