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 Yu-Xiang Wang

Yu-Xiang Wang

University of California Santa Barbara

Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings


May 21, 2021
Ming Yin, Yu-Xiang Wang

Figure 1 for Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings

  Access Paper or Ask Questions

Characterizing Uniform Convergence in Offline Policy Evaluation via model-based approach: Offline Learning, Task-Agnostic and Reward-Free


May 13, 2021
Ming Yin, Yu-Xiang Wang

Figure 1 for Characterizing Uniform Convergence in Offline Policy Evaluation via model-based approach: Offline Learning, Task-Agnostic and Reward-Free

  Access Paper or Ask Questions

Optimal Dynamic Regret in Exp-Concave Online Learning


Apr 23, 2021
Dheeraj Baby, Yu-Xiang Wang

Figure 1 for Optimal Dynamic Regret in Exp-Concave Online Learning
Figure 2 for Optimal Dynamic Regret in Exp-Concave Online Learning
Figure 3 for Optimal Dynamic Regret in Exp-Concave Online Learning
Figure 4 for Optimal Dynamic Regret in Exp-Concave Online Learning

  Access Paper or Ask Questions

Non-stationary Online Learning with Memory and Non-stochastic Control


Feb 07, 2021
Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou

Figure 1 for Non-stationary Online Learning with Memory and Non-stochastic Control

  Access Paper or Ask Questions

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction


Feb 02, 2021
Ming Yin, Yu Bai, Yu-Xiang Wang

Figure 1 for Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
Figure 2 for Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
Figure 3 for Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

  Access Paper or Ask Questions

An Optimal Reduction of TV-Denoising to Adaptive Online Learning


Jan 26, 2021
Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang

Figure 1 for An Optimal Reduction of TV-Denoising to Adaptive Online Learning
Figure 2 for An Optimal Reduction of TV-Denoising to Adaptive Online Learning
Figure 3 for An Optimal Reduction of TV-Denoising to Adaptive Online Learning
Figure 4 for An Optimal Reduction of TV-Denoising to Adaptive Online Learning
* To appear at AISTATS 2021 
  Access Paper or Ask Questions

Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning


Nov 13, 2020
Chong Liu, Yuqing Zhu, Kamalika Chaudhuri, Yu-Xiang Wang

Figure 1 for Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning

  Access Paper or Ask Questions

Inter-Series Attention Model for COVID-19 Forecasting


Oct 25, 2020
Xiaoyong Jin, Yu-Xiang Wang, Xifeng Yan

Figure 1 for Inter-Series Attention Model for COVID-19 Forecasting
Figure 2 for Inter-Series Attention Model for COVID-19 Forecasting
Figure 3 for Inter-Series Attention Model for COVID-19 Forecasting
Figure 4 for Inter-Series Attention Model for COVID-19 Forecasting
* 10 pages, 6 figures 
  Access Paper or Ask Questions

Voting-based Approaches For Differentially Private Federated Learning


Oct 09, 2020
Yuqing Zhu, Xiang Yu, Yi-Hsuan Tsai, Francesco Pittaluga, Masoud Faraki, Manmohan chandraker, Yu-Xiang Wang

Figure 1 for Voting-based Approaches For Differentially Private Federated Learning
Figure 2 for Voting-based Approaches For Differentially Private Federated Learning
Figure 3 for Voting-based Approaches For Differentially Private Federated Learning
Figure 4 for Voting-based Approaches For Differentially Private Federated Learning

  Access Paper or Ask Questions

Adaptive Online Estimation of Piecewise Polynomial Trends


Sep 30, 2020
Dheeraj Baby, Yu-Xiang Wang

Figure 1 for Adaptive Online Estimation of Piecewise Polynomial Trends
Figure 2 for Adaptive Online Estimation of Piecewise Polynomial Trends
Figure 3 for Adaptive Online Estimation of Piecewise Polynomial Trends
Figure 4 for Adaptive Online Estimation of Piecewise Polynomial Trends

  Access Paper or Ask Questions

Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning


Jul 07, 2020
Ming Yin, Yu Bai, Yu-Xiang Wang

Figure 1 for Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning
* Appendix included 
  Access Paper or Ask Questions

Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability


May 01, 2020
Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, Giovanni Vigna

Figure 1 for Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability
Figure 2 for Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability
Figure 3 for Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability
Figure 4 for Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability

  Access Paper or Ask Questions

Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift


Mar 10, 2020
Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoff Gordon

Figure 1 for Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Figure 2 for Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Figure 3 for Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift
Figure 4 for Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift

  Access Paper or Ask Questions

Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning


Jan 29, 2020
Ming Yin, Yu-Xiang Wang

Figure 1 for Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning
* Includes appendix. Accepted for AISTATS 2020 
  Access Paper or Ask Questions

Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting


Jun 29, 2019
Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, Xifeng Yan

Figure 1 for Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Figure 2 for Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Figure 3 for Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Figure 4 for Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting

  Access Paper or Ask Questions

Doubly Robust Crowdsourcing


Jun 08, 2019
Chong Liu, Yu-Xiang Wang

Figure 1 for Doubly Robust Crowdsourcing
Figure 2 for Doubly Robust Crowdsourcing
* presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA 
  Access Paper or Ask Questions

Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling


Jun 08, 2019
Tengyang Xie, Yifei Ma, Yu-Xiang Wang

Figure 1 for Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Figure 2 for Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Figure 3 for Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Figure 4 for Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling

  Access Paper or Ask Questions

Online Forecasting of Total-Variation-bounded Sequences


Jun 08, 2019
Dheeraj Baby, Yu-Xiang Wang

Figure 1 for Online Forecasting of Total-Variation-bounded Sequences
Figure 2 for Online Forecasting of Total-Variation-bounded Sequences
Figure 3 for Online Forecasting of Total-Variation-bounded Sequences
Figure 4 for Online Forecasting of Total-Variation-bounded Sequences

  Access Paper or Ask Questions

Provably Efficient Q-Learning with Low Switching Cost


May 30, 2019
Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang


  Access Paper or Ask Questions

A Higher-Order Kolmogorov-Smirnov Test


Mar 24, 2019
Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas, Ryan J. Tibshirani

Figure 1 for A Higher-Order Kolmogorov-Smirnov Test
Figure 2 for A Higher-Order Kolmogorov-Smirnov Test
Figure 3 for A Higher-Order Kolmogorov-Smirnov Test
Figure 4 for A Higher-Order Kolmogorov-Smirnov Test
* 18 pages, AISTATS 2019 
  Access Paper or Ask Questions

Imitation-Regularized Offline Learning


Jan 15, 2019
Yifei Ma, Yu-Xiang Wang, Balakrishnan, Narayanaswamy

Figure 1 for Imitation-Regularized Offline Learning
Figure 2 for Imitation-Regularized Offline Learning
Figure 3 for Imitation-Regularized Offline Learning
Figure 4 for Imitation-Regularized Offline Learning
* Accepted for publication at AISTATS 2019 
  Access Paper or Ask Questions

ProxQuant: Quantized Neural Networks via Proximal Operators


Oct 08, 2018
Yu Bai, Yu-Xiang Wang, Edo Liberty

Figure 1 for ProxQuant: Quantized Neural Networks via Proximal Operators
Figure 2 for ProxQuant: Quantized Neural Networks via Proximal Operators
Figure 3 for ProxQuant: Quantized Neural Networks via Proximal Operators
Figure 4 for ProxQuant: Quantized Neural Networks via Proximal Operators

  Access Paper or Ask Questions

signSGD: Compressed Optimisation for Non-Convex Problems


Aug 07, 2018
Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar

Figure 1 for signSGD: Compressed Optimisation for Non-Convex Problems
Figure 2 for signSGD: Compressed Optimisation for Non-Convex Problems
Figure 3 for signSGD: Compressed Optimisation for Non-Convex Problems
Figure 4 for signSGD: Compressed Optimisation for Non-Convex Problems

  Access Paper or Ask Questions

Subsampled Rényi Differential Privacy and Analytical Moments Accountant


Jul 31, 2018
Yu-Xiang Wang, Borja Balle, Shiva Kasiviswanathan

Figure 1 for Subsampled Rényi Differential Privacy and Analytical Moments Accountant

  Access Paper or Ask Questions

Detecting and Correcting for Label Shift with Black Box Predictors


Jul 26, 2018
Zachary C. Lipton, Yu-Xiang Wang, Alex Smola

Figure 1 for Detecting and Correcting for Label Shift with Black Box Predictors
Figure 2 for Detecting and Correcting for Label Shift with Black Box Predictors
Figure 3 for Detecting and Correcting for Label Shift with Black Box Predictors
Figure 4 for Detecting and Correcting for Label Shift with Black Box Predictors
* Published at the International Conference on Machine Learning (ICML) 2018 
  Access Paper or Ask Questions

Per-instance Differential Privacy


Jul 07, 2018
Yu-Xiang Wang

Figure 1 for Per-instance Differential Privacy
Figure 2 for Per-instance Differential Privacy
Figure 3 for Per-instance Differential Privacy

  Access Paper or Ask Questions

Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain


Jul 07, 2018
Yu-Xiang Wang

Figure 1 for Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
Figure 2 for Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
Figure 3 for Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
Figure 4 for Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain
* Uncertainty in Artificial Intelligence (UAI-2018), Monterey, CA 
  Access Paper or Ask Questions

Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising


Jun 07, 2018
Borja Balle, Yu-Xiang Wang

Figure 1 for Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Figure 2 for Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Figure 3 for Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
Figure 4 for Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
* To appear at the 35th International Conference on Machine Learning (ICML), 2018 
  Access Paper or Ask Questions

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


May 11, 2018
Xi Chen, Yining Wang, Yu-Xiang Wang

Figure 1 for Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures
Figure 2 for Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures
Figure 3 for Non-stationary Stochastic Optimization under $L_{p,q}$-Variation Measures
* 38 pages, 3 figures. Revised version 
  Access Paper or Ask Questions