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

Yuxin Chen

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

Figure 1 for Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence

  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

Figure 1 for Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting

  Access Paper or Ask Questions

Understanding the Effect of Bias in Deep Anomaly Detection


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

Figure 1 for Understanding the Effect of Bias in Deep Anomaly Detection
Figure 2 for Understanding the Effect of Bias in Deep Anomaly Detection
Figure 3 for Understanding the Effect of Bias in Deep Anomaly Detection
Figure 4 for Understanding the Effect of Bias in Deep Anomaly Detection
* 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

Figure 1 for Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation
Figure 2 for Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation
Figure 3 for Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation
Figure 4 for Generating Continuous Motion and Force Plans in Real-Time for Legged Mobile Manipulation

  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

Figure 1 for Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
Figure 2 for Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
Figure 3 for Towards an Interpretable Data-driven Trigger System for High-throughput Physics Facilities
* 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

Figure 1 for Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis
* 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

Figure 1 for Softmax Policy Gradient Methods Can Take Exponential Time to Converge
Figure 2 for Softmax Policy Gradient Methods Can Take Exponential Time to Converge
Figure 3 for Softmax Policy Gradient Methods Can Take Exponential Time to Converge
Figure 4 for Softmax Policy Gradient Methods Can Take Exponential Time to Converge

  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

Figure 1 for Tightening the Dependence on Horizon in the Sample Complexity of Q-Learning

  Access Paper or Ask Questions

Spectral Methods for Data Science: A Statistical Perspective


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

Figure 1 for Spectral Methods for Data Science: A Statistical Perspective
Figure 2 for Spectral Methods for Data Science: A Statistical Perspective
Figure 3 for Spectral Methods for Data Science: A Statistical Perspective
Figure 4 for Spectral Methods for Data Science: A Statistical Perspective

  Access Paper or Ask Questions

The Teaching Dimension of Kernel Perceptron


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

Figure 1 for The Teaching Dimension of Kernel Perceptron
Figure 2 for The Teaching Dimension of Kernel Perceptron
Figure 3 for The Teaching Dimension of Kernel Perceptron
Figure 4 for The Teaching Dimension of Kernel Perceptron

  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

Figure 1 for Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds
Figure 2 for Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds
Figure 3 for Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds
Figure 4 for Learning Time Varying Risk Preferences from Investment Portfolios using Inverse Optimization with Applications on Mutual Funds

  Access Paper or Ask Questions

Preference-Based Batch and Sequential Teaching


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

Figure 1 for Preference-Based Batch and Sequential Teaching
Figure 2 for Preference-Based Batch and Sequential Teaching
Figure 3 for Preference-Based Batch and Sequential Teaching
Figure 4 for Preference-Based Batch and Sequential Teaching
* 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

Figure 1 for Learning Mixtures of Low-Rank Models
Figure 2 for Learning Mixtures of Low-Rank Models
Figure 3 for Learning Mixtures of Low-Rank Models

  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

Figure 1 for Using Ensemble Classifiers to Detect Incipient Anomalies
Figure 2 for Using Ensemble Classifiers to Detect Incipient Anomalies
Figure 3 for Using Ensemble Classifiers to Detect Incipient Anomalies
Figure 4 for Using Ensemble Classifiers to Detect Incipient Anomalies
* 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

Figure 1 for Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
Figure 2 for Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
* 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

Figure 1 for Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution
Figure 2 for Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution
Figure 3 for Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution

  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

Figure 1 for Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
Figure 2 for Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
Figure 3 for Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
Figure 4 for Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
* 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

Figure 1 for Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?
Figure 2 for Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?
Figure 3 for Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?
Figure 4 for Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?

  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

Figure 1 for Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries
Figure 2 for Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries
Figure 3 for Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries

  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

Figure 1 for Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model

  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

Figure 1 for Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Figure 2 for Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Figure 3 for Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
Figure 4 for Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality
* Accepted in part to ICML 2020 
  Access Paper or Ask Questions

Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction


Jun 04, 2020
Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen

Figure 1 for Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction

  Access Paper or Ask Questions

Understanding the Power and Limitations of Teaching with Imperfect Knowledge


Mar 21, 2020
Rati Devidze, Farnam Mansouri, Luis Haug, Yuxin Chen, Adish Singla

Figure 1 for Understanding the Power and Limitations of Teaching with Imperfect Knowledge
Figure 2 for Understanding the Power and Limitations of Teaching with Imperfect Knowledge

  Access Paper or Ask Questions

An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles


Mar 03, 2020
Niklas Ã…kerblom, Yuxin Chen, Morteza Haghir Chehreghani

Figure 1 for An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles
Figure 2 for An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles
Figure 3 for An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles
Figure 4 for An Online Learning Framework for Energy-Efficient Navigation of Electric Vehicles

  Access Paper or Ask Questions

A Financial Service Chatbot based on Deep Bidirectional Transformers


Feb 17, 2020
Shi Yu, Yuxin Chen, Hussain Zaidi

Figure 1 for A Financial Service Chatbot based on Deep Bidirectional Transformers
Figure 2 for A Financial Service Chatbot based on Deep Bidirectional Transformers
Figure 3 for A Financial Service Chatbot based on Deep Bidirectional Transformers
Figure 4 for A Financial Service Chatbot based on Deep Bidirectional Transformers

  Access Paper or Ask Questions