Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Yuxin Chen

Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning


Oct 09, 2021
Gen Li, Laixi Shi, Yuxin Chen, Yuantao Gu, Yuejie Chi

* Short version in Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021) 

  Access Paper or Ask Questions

Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition


Aug 23, 2021
Yuxin Chen, Ziqi Zhang, Chunfeng Yuan, Bing Li, Ying Deng, Weiming Hu

* Accepted to ICCV2021. Camera-ready version with supplementary materials. Code is available at https://github.com/Uason-Chen/CTR-GCN 

  Access Paper or Ask Questions

A Contract Theory based Incentive Mechanism for Federated Learning


Aug 12, 2021
Mengmeng Tian, Yuxin Chen, Yuan Liu, Zehui Xiong, Cyril Leung, Chunyan Miao

* 7 pages, 2 figures, International Workshop on Federated and Transfer Learning for Data Sparsity and Confidentiality in Conjunction with IJCAI 2021 (FTL-IJCAI'21), Best Student Paper Award 

  Access Paper or Ask Questions

Inference for Heteroskedastic PCA with Missing Data


Jul 26, 2021
Yuling Yan, Yuxin Chen, Jianqing Fan


  Access Paper or Ask Questions

Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence


May 24, 2021
Wenhao Zhan, Shicong Cen, Baihe Huang, Yuxin Chen, Jason D. Lee, Yuejie Chi


  Access Paper or Ask Questions

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting


May 17, 2021
Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei


  Access Paper or Ask Questions

Understanding the Effect of Bias in Deep Anomaly Detection


May 16, 2021
Ziyu Ye, Yuxin Chen, Haitao Zheng

* Accepted at IJCAI '21. Codes available on github.com/ZIYU-DEEP/Understanding-Bias-in-Deep-Anomaly-Detection-PyTorch 

  Access Paper or Ask Questions

Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation


Apr 23, 2021
Parker Ewen, Jean-Pierre Sleiman, Yuxin Chen, Wei-Chun Lu, Marco Hutter, Ram Vasudevan


  Access Paper or Ask Questions

Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities


Apr 14, 2021
Chinmaya Mahesh, Kristin Dona, David W. Miller, Yuxin Chen

* Appeared in the 3rd Workshop on Machine Learning and the Physical Sciences, NeurIPS 2020 

  Access Paper or Ask Questions

Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps


Apr 07, 2021
Gen Li, Changxiao Cai, Yuantao Gu, H. Vincent Poor, Yuxin Chen


  Access Paper or Ask Questions

Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis


Mar 16, 2021
Gen Li, Changxiao Cai, Yuxin Chen, Yuantao Gu, Yuting Wei, Yuejie Chi

* v2 added a matching lower bound, and removed the finite-horizon setting for brevity 

  Access Paper or Ask Questions

Softmax Policy Gradient Methods Can Take Exponential Time to Converge


Feb 22, 2021
Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen


  Access Paper or Ask Questions

Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning


Feb 12, 2021
Gen Li, Changxiao Cai, Yuxin Chen, Yuantao Gu, Yuting Wei, Yuejie Chi


  Access Paper or Ask Questions

Spectral Methods for Data Science: A Statistical Perspective


Dec 15, 2020
Yuxin Chen, Yuejie Chi, Jianqing Fan, Cong Ma


  Access Paper or Ask Questions

The Teaching Dimension of Kernel Perceptron


Oct 27, 2020
Akash Kumar, Hanqi Zhang, Adish Singla, Yuxin Chen


  Access Paper or Ask Questions

Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds


Oct 22, 2020
Shi Yu, Yuxin Chen, Chaosheng Dong


  Access Paper or Ask Questions

Preference-Based Batch and Sequential Teaching


Oct 17, 2020
Farnam Mansouri, Yuxin Chen, Ara Vartanian, Xiaojin Zhu, Adish Singla

* arXiv admin note: substantial text overlap with arXiv:1910.10944 

  Access Paper or Ask Questions

Learning Mixtures of Low-Rank Models


Sep 23, 2020
Yanxi Chen, Cong Ma, H. Vincent Poor, Yuxin Chen


  Access Paper or Ask Questions

Using Ensemble Classifiers to Detect Incipient Anomalies


Aug 20, 2020
Baihong Jin, Yingshui Tan, Albert Liu, Xiangyu Yue, Yuxin Chen, Alberto Sangiovanni Vincentelli

* Submitted to Transactions on Cyber-Physical Systems for Special Issue on AI and Cyber-Physical Systems 

  Access Paper or Ask Questions

Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization


Aug 10, 2020
Shicong Cen, Chen Cheng, Yuxin Chen, Yuting Wei, Yuejie Chi

* V2 adds new proofs and improved results 

  Access Paper or Ask Questions

Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution


Aug 04, 2020
Yuxin Chen, Jianqing Fan, Bingyan Wang, Yuling Yan


  Access Paper or Ask Questions

Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI


Jul 12, 2020
Yingshui Tan, Baihong Jin, Xiangyu Yue, Yuxin Chen, Alberto Sangiovanni Vincentelli

* Preprint of submission to NeurIPS 2020 

  Access Paper or Ask Questions

Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?


Jul 08, 2020
Baihong Jin, Yingshui Tan, Yuxin Chen, Kameshwar Poolla, Alberto Sangiovanni Vincentelli


  Access Paper or Ask Questions

Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries


Jun 25, 2020
Akash Kumar, Adish Singla, Yisong Yue, Yuxin Chen


  Access Paper or Ask Questions

Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model


Jun 17, 2020
Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen


  Access Paper or Ask Questions

Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality


Jun 15, 2020
Changxiao Cai, H. Vincent Poor, Yuxin Chen

* Accepted in part to ICML 2020 

  Access Paper or Ask Questions