Search Results for author: Lin Chen

Found 67 papers, 9 papers with code

Naive Markowitz Policies

no code implementations14 Dec 2022 Lin Chen, Xun Yu Zhou

We study a continuous-time Markowitz mean-variance portfolio selection model in which a naive agent, unaware of the underlying time-inconsistency, continuously reoptimizes over time.

FedRule: Federated Rule Recommendation System with Graph Neural Networks

no code implementations13 Nov 2022 Yuhang Yao, Mohammad Mahdi Kamani, Zhongwei Cheng, Lin Chen, Carlee Joe-Wong, Tianqiang Liu

Much of the value that IoT (Internet-of-Things) devices bring to ``smart'' homes lies in their ability to automatically trigger other devices' actions: for example, a smart camera triggering a smart lock to unlock a door.

Link Prediction Recommendation Systems

Sequential Attention for Feature Selection

no code implementations29 Sep 2022 Mohammadhossein Bateni, Lin Chen, Matthew Fahrbach, Gang Fu, Vahab Mirrokni, Taisuke Yasuda

Feature selection is the problem of selecting a subset of features for a machine learning model that maximizes model quality subject to a resource budget constraint.

Feature Importance

GATraj: A Graph- and Attention-based Multi-Agent Trajectory Prediction Model

1 code implementation16 Sep 2022 Hao Cheng, Mengmeng Liu, Lin Chen, Hellward Broszio, Monika Sester, Michael Ying Yang

Our model achieves performance on par with the state-of-the-art models at a much higher prediction speed tested on multiple open datasets.

Autonomous Driving Robot Navigation +1

Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation

1 code implementation16 Sep 2022 Lin Chen, Zhixiang Wei, Xin Jin, Huaian Chen, Miao Zheng, Kai Chen, Yi Jin

In this work, we resort to data mixing to establish a deliberated domain bridging (DDB) for DASS, through which the joint distributions of source and target domains are aligned and interacted with each in the intermediate space.

Knowledge Distillation Semantic Segmentation +3

Wideband Channel Estimation for mmWave MIMO Systems with Beam Squint

no code implementations6 Sep 2022 Li Ge, Xue Jiang, Lin Chen, Qibo Qin, Xingzhao Liu

With the scale of antenna arrays and the bandwidth increasing, many existing narrowband channel estimation methods ignoring the effect of beam squint may face severe performance degradation in wideband millimeter-wave (mmWave) communication systems.

Collaboration in Participant-Centric Federated Learning: A Game-Theoretical Perspective

no code implementations25 Jul 2022 Guangjing Huang, Xu Chen, Tao Ouyang, Qian Ma, Lin Chen, Junshan Zhang

To coordinate the selfish and heterogeneous participants, we propose a novel analytic framework for incentivizing effective and efficient collaborations for participant-centric FL.

Federated Learning

Package Theft Detection from Smart Home Security Cameras

no code implementations24 May 2022 Hung-Min Hsu, Xinyu Yuan, Baohua Zhu, Zhongwei Cheng, Lin Chen

Package theft detection has been a challenging task mainly due to lack of training data and a wide variety of package theft cases in reality.

Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network

1 code implementation17 Apr 2022 Yuhang He, Lin Chen, Junkun Xie, Long Chen

This motivates us to conduct a "task transfer" paradigm so that 3D semantic segmentation benefits from aggregating 2D semantic cues, albeit pose noises are contained in 2D image observations.

2D Semantic Segmentation 3D Semantic Segmentation

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

1 code implementation CVPR 2022 Lin Chen, Huaian Chen, Zhixiang Wei, Xin Jin, Xiao Tan, Yi Jin, Enhong Chen

Such NWD can be coupled with the classifier to serve as a discriminator satisfying the K-Lipschitz constraint without the requirements of additional weight clipping or gradient penalty strategy.

Unsupervised Domain Adaptation

Youling: an AI-Assisted Lyrics Creation System

no code implementations EMNLP 2020 Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang

In the lyrics generation process, \textit{Youling} supports traditional one pass full-text generation mode as well as an interactive generation mode, which allows users to select the satisfactory sentences from generated candidates conditioned on preceding context.

Text Generation

Portfolio optimization with idiosyncratic and systemic risks for financial networks

no code implementations22 Nov 2021 Yajie Yang, Longfeng Zhao, Lin Chen, Chao Wang, Jihui Han

The two risks are measured by the idiosyncratic variance and the network clustering coefficient derived from the asset correlation networks, respectively.

Portfolio Optimization

Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation

1 code implementation19 Oct 2021 Sumanth Chennupati, Mohammad Mahdi Kamani, Zhongwei Cheng, Lin Chen

Despite this advancement in different techniques for distilling the knowledge, the aggregation of different paths for distillation has not been studied comprehensively.

Knowledge Distillation Neural Network Compression +3

Spectral Multiplicity Entails Sample-wise Multiple Descent

no code implementations29 Sep 2021 Lin Chen, Song Mei

Moreover, we theoretically show that the ridge estimator with optimal regularization can result in a monotone generalization risk curve and thereby eliminate multiple descent under some assumptions.

Feature Cross Search via Submodular Optimization

no code implementations5 Jul 2021 Lin Chen, Hossein Esfandiari, Gang Fu, Vahab S. Mirrokni, Qian Yu

First, we show that it is not possible to provide an $n^{1/\log\log n}$-approximation algorithm for this problem unless the exponential time hypothesis fails.

Feature Engineering

When Few-Shot Learning Meets Video Object Detection

no code implementations26 Mar 2021 Zhongjie Yu, Gaoang Wang, Lin Chen, Sebastian Raschka, Jiebo Luo

We employ a transfer-learning framework to effectively train the video object detector on a large number of base-class objects and a few video clips of novel-class objects.

Few-Shot Video Object Detection object-detection +2

Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm

no code implementations17 Mar 2021 Lin Chen, Bruno Scherrer, Peter L. Bartlett

In this regime, for any $q\in[\gamma^{2}, 1]$, we can construct a hard instance such that the smallest eigenvalue of its feature covariance matrix is $q/d$ and it requires $\Omega\left(\frac{d}{\gamma^{2}\left(q-\gamma^{2}\right)\varepsilon^{2}}\exp\left(\Theta\left(d\gamma^{2}\right)\right)\right)$ samples to approximate the value function up to an additive error $\varepsilon$.

Off-policy evaluation

Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models

1 code implementation7 Mar 2021 Linghan Meng, Yanhui Li, Lin Chen, Zhi Wang, Di wu, Yuming Zhou, Baowen Xu

To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.

Bending the Bruhat-Tits Tree I:Tensor Network and Emergent Einstein Equations

no code implementations24 Feb 2021 Lin Chen, Xirong Liu, Ling-Yan Hung

In fact we demonstrate that a unique (up to normalizations) emergent graph Einstein equation is satisfied by the geometric data encoded in the tensor network, and the graph Einstein tensor automatically recovers the known proposal in the mathematics literature, at least perturbatively order by order in the deformation away from the pure Bruhat-Tits Tree geometry dual to pure CFTs.

High Energy Physics - Theory Strongly Correlated Electrons General Relativity and Quantum Cosmology Mathematical Physics Mathematical Physics Quantum Physics

Emergent Einstein Equation in p-adic CFT Tensor Networks

no code implementations24 Feb 2021 Lin Chen, Xirong Liu, Ling-Yan Hung

We take the tensor network describing explicit p-adic CFT partition functions proposed in [1], and considered boundary conditions of the network describing a deformed Bruhat-Tits (BT) tree geometry.

Tensor Networks High Energy Physics - Theory Strongly Correlated Electrons General Relativity and Quantum Cosmology Mathematical Physics Mathematical Physics Quantum Physics

Bending the Bruhat-Tits Tree II: the p-adic BTZ Black hole and Local Diffeomorphism on the Bruhat-Tits Tree

no code implementations24 Feb 2021 Lin Chen, Xirong Liu, Ling-Yan Hung

In this sequel to [1], we take up a second approach in bending the Bruhat-Tits tree.

High Energy Physics - Theory Strongly Correlated Electrons General Relativity and Quantum Cosmology Mathematical Physics Mathematical Physics Quantum Physics

Genuine entanglement, distillability and quantum information masking under noise

no code implementations1 Feb 2021 Mengyao Hu, Lin Chen

Genuineness and distillability of entanglement play a key role in quantum information tasks, and they are easily disturbed by the noise.

Quantum Physics

EDSC: An Event-Driven Smart Contract Platform

no code implementations14 Jan 2021 Mudabbir Kaleem, Keshav Kasichainula, Rabimba Karanjai, Lei Xu, Zhimin Gao, Lin Chen, Weidong Shi

This paper presents EDSC, a novel smart contract platform design based on the event-driven execution model as opposed to the traditionally employed transaction-driven execution model.

Distributed, Parallel, and Cluster Computing

DAIL: Dataset-Aware and Invariant Learning for Face Recognition

no code implementations14 Jan 2021 Gaoang Wang, Lin Chen, Tianqiang Liu, Mingwei He, Jiebo Luo

To solve the first issue of identity overlapping, we propose a dataset-aware loss for multi-dataset training by reducing the penalty when the same person appears in multiple datasets.

Domain Adaptation Face Recognition

Sequential Resource Access: Theory and Algorithm

no code implementations7 Dec 2020 Lin Chen, Anastasios Giovanidis, Wei Wang, Lin Shan

We formulate and analyze a generic sequential resource access problem arising in a variety of engineering fields, where a user disposes a number of heterogeneous computing, communication, or storage resources, each characterized by the probability of successfully executing the user's task and the related access delay and cost, and seeks an optimal access strategy to maximize her utility within a given time horizon, defined as the expected reward minus the access cost.

Networking and Internet Architecture

Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHS

no code implementations ICLR 2021 Lin Chen, Sheng Xu

We prove that the reproducing kernel Hilbert spaces (RKHS) of a deep neural tangent kernel and the Laplace kernel include the same set of functions, when both kernels are restricted to the sphere $\mathbb{S}^{d-1}$.

Region Comparison Network for Interpretable Few-shot Image Classification

1 code implementation8 Sep 2020 Zhiyu Xue, Lixin Duan, Wen Li, Lin Chen, Jiebo Luo

For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets.

Classification Few-Shot Image Classification +2

Multiple Descent: Design Your Own Generalization Curve

no code implementations NeurIPS 2021 Lin Chen, Yifei Min, Mikhail Belkin, Amin Karbasi

This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized.

regression

Joint Multi-User DNN Partitioning and Computational Resource Allocation for Collaborative Edge Intelligence

no code implementations15 Jul 2020 Xin Tang, Xu Chen, Liekang Zeng, Shuai Yu, Lin Chen

With the assistance of edge servers, user equipments (UEs) are able to run deep neural network (DNN) based AI applications, which are generally resource-hungry and compute-intensive, such that an individual UE can hardly afford by itself in real time.

Edge-computing

Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding

no code implementations11 Jul 2020 Jinhai Yang, Hua Yang, Lin Chen

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning.

Classification Few-Shot Learning +1

Meta Learning in the Continuous Time Limit

no code implementations19 Jun 2020 Ruitu Xu, Lin Chen, Amin Karbasi

In this paper, we establish the ordinary differential equation (ODE) that underlies the training dynamics of Model-Agnostic Meta-Learning (MAML).

Meta-Learning

Hybrid Cryptocurrency Pump and Dump Detection

no code implementations14 Mar 2020 Hadi Mansourifar, Lin Chen, Weidong Shi

In this paper, we propose a novel hybrid pump and dump detection method based on distance and density metrics.

Anomaly Detection Time Series

The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization

no code implementations25 Feb 2020 Yifei Min, Lin Chen, Amin Karbasi

In the medium adversary regime, with more training data, the generalization loss exhibits a double descent curve, which implies the existence of an intermediate stage where more training data hurts the generalization.

Classification General Classification

Deep Fusion of Local and Non-Local Features for Precision Landslide Recognition

1 code implementation20 Feb 2020 Qing Zhu, Lin Chen, Han Hu, Binzhi Xu, Yeting Zhang, Haifeng Li

The second uses a scale attention mechanism to guide the up-sampling of features from the coarse level by a learned weight map.

Semantic Segmentation

More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models

no code implementations ICML 2020 Lin Chen, Yifei Min, Mingrui Zhang, Amin Karbasi

Despite remarkable success in practice, modern machine learning models have been found to be susceptible to adversarial attacks that make human-imperceptible perturbations to the data, but result in serious and potentially dangerous prediction errors.

An Adaptive and Fast Convergent Approach to Differentially Private Deep Learning

no code implementations19 Dec 2019 Zhiying Xu, Shuyu Shi, Alex X. Liu, Jun Zhao, Lin Chen

ADADP significantly reduces the privacy cost by improving the convergence speed with an adaptive learning rate and mitigates the negative effect of differential privacy upon the model accuracy by introducing adaptive noise.

TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning

no code implementations CVPR 2020 Zhongjie Yu, Lin Chen, Zhongwei Cheng, Jiebo Luo

Under the proposed framework, we develop a novel method for semi-supervised few-shot learning called TransMatch by instantiating the three components with Imprinting and MixMatch.

Few-Shot Learning Transfer Learning

Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation

no code implementations Findings of the Association for Computational Linguistics 2020 Yiming Xu, Lin Chen, Zhongwei Cheng, Lixin Duan, Jiebo Luo

A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains.

Domain Adaptation Question Answering +1

Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond

no code implementations NeurIPS 2019 Lin Chen, Hossein Esfandiari, Thomas Fu, Vahab S. Mirrokni

In this paper, we aim to develop LSH schemes for distance functions that measure the distance between two probability distributions, particularly for f-divergences as well as a generalization to capture mutual information loss.

Model Compression

Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition

no code implementations NeurIPS 2020 Lin Chen, Qian Yu, Hannah Lawrence, Amin Karbasi

To establish the dimension-independent upper bound, we next show that a mini-batching algorithm provides an $ O(\frac{T}{\sqrt{K}}) $ upper bound, and therefore conclude that the minimax regret of switching-constrained OCO is $ \Theta(\frac{T}{\sqrt{K}}) $ for any $K$.

Generative Imaging and Image Processing via Generative Encoder

no code implementations23 May 2019 Lin Chen, Haizhao Yang

This paper introduces a novel generative encoder (GE) model for generative imaging and image processing with applications in compressed sensing and imaging, image compression, denoising, inpainting, deblurring, and super-resolution.

Deblurring Denoising +2

Known-class Aware Self-ensemble for Open Set Domain Adaptation

1 code implementation3 May 2019 Qing Lian, Wen Li, Lin Chen, Lixin Duan

Particularly, in open set domain adaptation, we allow the classes from the source and target domains to be partially overlapped.

Domain Adaptation

Categorical Feature Compression via Submodular Optimization

no code implementations30 Apr 2019 Mohammadhossein Bateni, Lin Chen, Hossein Esfandiari, Thomas Fu, Vahab S. Mirrokni, Afshin Rostamizadeh

To achieve this, we introduce a novel re-parametrization of the mutual information objective, which we prove is submodular, and design a data structure to query the submodular function in amortized $O(\log n )$ time (where $n$ is the input vocabulary size).

Black Box Submodular Maximization: Discrete and Continuous Settings

no code implementations28 Jan 2019 Lin Chen, Mingrui Zhang, Hamed Hassani, Amin Karbasi

In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided.

Unconstrained Submodular Maximization with Constant Adaptive Complexity

no code implementations15 Nov 2018 Lin Chen, Moran Feldman, Amin Karbasi

In this paper, we consider the unconstrained submodular maximization problem.

Election with Bribed Voter Uncertainty: Hardness and Approximation Algorithm

no code implementations7 Nov 2018 Lin Chen, Lei Xu, Shouhuai Xu, Zhimin Gao, Weidong Shi

In this paper, we introduce a novel variant of the bribery problem, "Election with Bribed Voter Uncertainty" or BVU for short, accommodating the uncertainty that the vote of a bribed voter may or may not be counted.

Projection-Free Bandit Convex Optimization

no code implementations18 May 2018 Lin Chen, Mingrui Zhang, Amin Karbasi

In this paper, we propose the first computationally efficient projection-free algorithm for bandit convex optimization (BCO).

Matrix Completion

Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity

no code implementations ICML 2018 Lin Chen, Christopher Harshaw, Hamed Hassani, Amin Karbasi

We also propose One-Shot Frank-Wolfe, a simpler algorithm which requires only a single stochastic gradient estimate in each round and achieves an $O(T^{2/3})$ stochastic regret bound for convex and continuous submodular optimization.

Comparison Based Learning from Weak Oracles

no code implementations20 Feb 2018 Ehsan Kazemi, Lin Chen, Sanjoy Dasgupta, Amin Karbasi

More specifically, we aim at devising efficient algorithms to locate a target object in a database equipped with a dissimilarity metric via invocation of the weak comparison oracle.

Online Continuous Submodular Maximization

no code implementations16 Feb 2018 Lin Chen, Hamed Hassani, Amin Karbasi

For such settings, we then propose an online stochastic gradient ascent algorithm that also achieves a regret bound of $O(\sqrt{T})$ regret, albeit against a weaker $1/2$-approximation to the best feasible solution in hindsight.

Interactive Submodular Bandit

no code implementations NeurIPS 2017 Lin Chen, Andreas Krause, Amin Karbasi

We then receive a noisy feedback about the utility of the action (e. g., ratings) which we model as a submodular function over the context-action space.

Data Summarization Movie Recommendation +1

Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?

no code implementations ICML 2018 Lin Chen, Moran Feldman, Amin Karbasi

In this paper, we prove that a randomized version of the greedy algorithm (previously used by Buchbinder et al. (2014) for a different problem) achieves an approximation ratio of $(1 + 1/\gamma)^{-2}$ for the maximization of a weakly submodular function subject to a general matroid constraint, where $\gamma$ is a parameter measuring the distance of the function from submodularity.

Submodular Variational Inference for Network Reconstruction

no code implementations29 Mar 2016 Lin Chen, Forrest W. Crawford, Amin Karbasi

In real-world and online social networks, individuals receive and transmit information in real time.

Variational Inference

Near-Optimal Active Learning of Halfspaces via Query Synthesis in the Noisy Setting

no code implementations11 Mar 2016 Lin Chen, Hamed Hassani, Amin Karbasi

This problem has recently gained a lot of interest in automated science and adversarial reverse engineering for which only heuristic algorithms are known.

Active Learning

Seeing the Unseen Network: Inferring Hidden Social Ties from Respondent-Driven Sampling

no code implementations13 Nov 2015 Lin Chen, Forrest W. Crawford, Amin Karbasi

Learning about the social structure of hidden and hard-to-reach populations --- such as drug users and sex workers --- is a major goal of epidemiological and public health research on risk behaviors and disease prevention.

Stochastic Optimization Time Series

Recognizing RGB Images by Learning from RGB-D Data

no code implementations CVPR 2014 Lin Chen, Wen Li, Dong Xu

In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images.

Object Recognition Unsupervised Domain Adaptation

Event Recognition in Videos by Learning from Heterogeneous Web Sources

no code implementations CVPR 2013 Lin Chen, Lixin Duan, Dong Xu

In this work, we propose to leverage a large number of loosely labeled web videos (e. g., from YouTube) and web images (e. g., from Google/Bing image search) for visual event recognition in consumer videos without requiring any labeled consumer videos.

Domain Adaptation Image Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.