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 Zheng Wen

Zheng Wen

Neural Contextual Bandits with Deep Representation and Shallow Exploration


Dec 03, 2020
Pan Xu, Zheng Wen, Handong Zhao, Quanquan Gu

Figure 1 for Neural Contextual Bandits with Deep Representation and Shallow Exploration
Figure 2 for Neural Contextual Bandits with Deep Representation and Shallow Exploration
* 28 pages, 1 figure, 1 table 
  Access Paper or Ask Questions

A Benchmark and Baseline for Language-Driven Image Editing


Oct 05, 2020
Jing Shi, Ning Xu, Trung Bui, Franck Dernoncourt, Zheng Wen, Chenliang Xu

Figure 1 for A Benchmark and Baseline for Language-Driven Image Editing
Figure 2 for A Benchmark and Baseline for Language-Driven Image Editing
Figure 3 for A Benchmark and Baseline for Language-Driven Image Editing
Figure 4 for A Benchmark and Baseline for Language-Driven Image Editing
* Accepted by ACCV 2020 
  Access Paper or Ask Questions

On the Sample Complexity of Reinforcement Learning with Policy Space Generalization


Aug 17, 2020
Wenlong Mou, Zheng Wen, Xi Chen


  Access Paper or Ask Questions

Low-rank Tensor Bandits


Jul 31, 2020
Botao Hao, Jie Zhou, Zheng Wen, Will Wei Sun

Figure 1 for Low-rank Tensor Bandits
Figure 2 for Low-rank Tensor Bandits
Figure 3 for Low-rank Tensor Bandits
Figure 4 for Low-rank Tensor Bandits

  Access Paper or Ask Questions

Structured Policy Iteration for Linear Quadratic Regulator


Jul 13, 2020
Youngsuk Park, Ryan A. Rossi, Zheng Wen, Gang Wu, Handong Zhao

Figure 1 for Structured Policy Iteration for Linear Quadratic Regulator
Figure 2 for Structured Policy Iteration for Linear Quadratic Regulator
Figure 3 for Structured Policy Iteration for Linear Quadratic Regulator
Figure 4 for Structured Policy Iteration for Linear Quadratic Regulator

  Access Paper or Ask Questions

Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems


Jul 09, 2020
Tong Yu, Branislav Kveton, Zheng Wen, Ruiyi Zhang, Ole J. Mengshoel

Figure 1 for Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Figure 2 for Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Figure 3 for Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
Figure 4 for Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems

  Access Paper or Ask Questions

Hypermodels for Exploration


Jun 12, 2020
Vikranth Dwaracherla, Xiuyuan Lu, Morteza Ibrahimi, Ian Osband, Zheng Wen, Benjamin Van Roy

Figure 1 for Hypermodels for Exploration
Figure 2 for Hypermodels for Exploration
Figure 3 for Hypermodels for Exploration
Figure 4 for Hypermodels for Exploration
* Published as a conference paper at ICLR 2020 
  Access Paper or Ask Questions

Improving Adversarial Text Generation by Modeling the Distant Future


May 04, 2020
Ruiyi Zhang, Changyou Chen, Zhe Gan, Wenlin Wang, Dinghan Shen, Guoyin Wang, Zheng Wen, Lawrence Carin

Figure 1 for Improving Adversarial Text Generation by Modeling the Distant Future
Figure 2 for Improving Adversarial Text Generation by Modeling the Distant Future
Figure 3 for Improving Adversarial Text Generation by Modeling the Distant Future
Figure 4 for Improving Adversarial Text Generation by Modeling the Distant Future
* ACL 2020. arXiv admin note: substantial text overlap with arXiv:1811.00696 
  Access Paper or Ask Questions

Nested-Wasserstein Self-Imitation Learning for Sequence Generation


Jan 20, 2020
Ruiyi Zhang, Changyou Chen, Zhe Gan, Zheng Wen, Wenlin Wang, Lawrence Carin

Figure 1 for Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Figure 2 for Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Figure 3 for Nested-Wasserstein Self-Imitation Learning for Sequence Generation
Figure 4 for Nested-Wasserstein Self-Imitation Learning for Sequence Generation
* Accepted by AISTATS2020 
  Access Paper or Ask Questions

Bootstrapping Upper Confidence Bound


Jul 23, 2019
Botao Hao, Yasin Abbasi-Yadkori, Zheng Wen, Guang Cheng

Figure 1 for Bootstrapping Upper Confidence Bound
Figure 2 for Bootstrapping Upper Confidence Bound
Figure 3 for Bootstrapping Upper Confidence Bound
Figure 4 for Bootstrapping Upper Confidence Bound

  Access Paper or Ask Questions

Waterfall Bandits: Learning to Sell Ads Online


Apr 20, 2019
Branislav Kveton, Saied Mahdian, S. Muthukrishnan, Zheng Wen, Yikun Xian

Figure 1 for Waterfall Bandits: Learning to Sell Ads Online
Figure 2 for Waterfall Bandits: Learning to Sell Ads Online
Figure 3 for Waterfall Bandits: Learning to Sell Ads Online
Figure 4 for Waterfall Bandits: Learning to Sell Ads Online

  Access Paper or Ask Questions

Stochastic Online Learning with Probabilistic Graph Feedback


Mar 04, 2019
Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung


  Access Paper or Ask Questions

Scalable Thompson Sampling via Optimal Transport


Feb 19, 2019
Ruiyi Zhang, Zheng Wen, Changyou Chen, Lawrence Carin

Figure 1 for Scalable Thompson Sampling via Optimal Transport
Figure 2 for Scalable Thompson Sampling via Optimal Transport
Figure 3 for Scalable Thompson Sampling via Optimal Transport
Figure 4 for Scalable Thompson Sampling via Optimal Transport
* Infer to Control Workshop on Probabilistic Reinforcement Learning and Structured Control at NIPS 2018; Long version accepted by AISTATS 2019 
  Access Paper or Ask Questions

Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits


Nov 13, 2018
Branislav Kveton, Csaba Szepesvari, Zheng Wen, Mohammad Ghavamzadeh, Tor Lattimore

Figure 1 for Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits
Figure 2 for Garbage In, Reward Out: Bootstrapping Exploration in Multi-Armed Bandits

  Access Paper or Ask Questions

Online Diverse Learning to Rank from Partial-Click Feedback


Nov 01, 2018
Prakhar Gupta, Gaurush Hiranandani, Harvineet Singh, Branislav Kveton, Zheng Wen, Iftikhar Ahamath Burhanuddin

Figure 1 for Online Diverse Learning to Rank from Partial-Click Feedback
Figure 2 for Online Diverse Learning to Rank from Partial-Click Feedback
Figure 3 for Online Diverse Learning to Rank from Partial-Click Feedback
Figure 4 for Online Diverse Learning to Rank from Partial-Click Feedback
* The first three authors contributed equally to this work. 24 pages, 4 figures, 1 table 
  Access Paper or Ask Questions

Posterior Sampling for Large Scale Reinforcement Learning


Oct 22, 2018
Georgios Theocharous, Zheng Wen, Yasin Abbasi-Yadkori, Nikos Vlassis

Figure 1 for Posterior Sampling for Large Scale Reinforcement Learning
Figure 2 for Posterior Sampling for Large Scale Reinforcement Learning
Figure 3 for Posterior Sampling for Large Scale Reinforcement Learning

  Access Paper or Ask Questions

Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback


Jun 19, 2018
Zheng Wen, Branislav Kveton, Michal Valko, Sharan Vaswani

Figure 1 for Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
Figure 2 for Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
Figure 3 for Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback
* Z. Wen, B. Kveton, M. Valko, and S. Vaswani, "Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback", Advances in Neural Information Processing Systems 30 Proceedings, 2017 
 * Compared with the previous version, this version has fixed a mistake. This version is also consistent with the NIPS camera-ready version 
  Access Paper or Ask Questions

Offline Evaluation of Ranking Policies with Click Models


Jun 13, 2018
Shuai Li, Yasin Abbasi-Yadkori, Branislav Kveton, S. Muthukrishnan, Vishwa Vinay, Zheng Wen

Figure 1 for Offline Evaluation of Ranking Policies with Click Models
Figure 2 for Offline Evaluation of Ranking Policies with Click Models
Figure 3 for Offline Evaluation of Ranking Policies with Click Models
Figure 4 for Offline Evaluation of Ranking Policies with Click Models

  Access Paper or Ask Questions

Deep Exploration via Randomized Value Functions


Jun 06, 2018
Ian Osband, Benjamin Van Roy, Daniel Russo, Zheng Wen

Figure 1 for Deep Exploration via Randomized Value Functions
Figure 2 for Deep Exploration via Randomized Value Functions
Figure 3 for Deep Exploration via Randomized Value Functions
Figure 4 for Deep Exploration via Randomized Value Functions

  Access Paper or Ask Questions

Conservative Exploration using Interleaving


Jun 03, 2018
Sumeet Katariya, Branislav Kveton, Zheng Wen, Vamsi K. Potluru

Figure 1 for Conservative Exploration using Interleaving

  Access Paper or Ask Questions

Model-Independent Online Learning for Influence Maximization


May 24, 2018
Sharan Vaswani, Branislav Kveton, Zheng Wen, Mohammad Ghavamzadeh, Laks Lakshmanan, Mark Schmidt

Figure 1 for Model-Independent Online Learning for Influence Maximization
Figure 2 for Model-Independent Online Learning for Influence Maximization
Figure 3 for Model-Independent Online Learning for Influence Maximization

  Access Paper or Ask Questions

New Insights into Bootstrapping for Bandits


May 24, 2018
Sharan Vaswani, Branislav Kveton, Zheng Wen, Anup Rao, Mark Schmidt, Yasin Abbasi-Yadkori

Figure 1 for New Insights into Bootstrapping for Bandits
Figure 2 for New Insights into Bootstrapping for Bandits
Figure 3 for New Insights into Bootstrapping for Bandits
Figure 4 for New Insights into Bootstrapping for Bandits

  Access Paper or Ask Questions

SpectralLeader: Online Spectral Learning for Single Topic Models


Apr 26, 2018
Tong Yu, Branislav Kveton, Zheng Wen, Hung Bui, Ole J. Mengshoel

Figure 1 for SpectralLeader: Online Spectral Learning for Single Topic Models
Figure 2 for SpectralLeader: Online Spectral Learning for Single Topic Models
* 17 pages, 2 figures 
  Access Paper or Ask Questions

Nearly Optimal Adaptive Procedure for Piecewise-Stationary Bandit: a Change-Point Detection Approach


Feb 17, 2018
Yang Cao, Zheng Wen, Branislav Kveton, Yao Xie

Figure 1 for Nearly Optimal Adaptive Procedure for Piecewise-Stationary Bandit: a Change-Point Detection Approach
Figure 2 for Nearly Optimal Adaptive Procedure for Piecewise-Stationary Bandit: a Change-Point Detection Approach
Figure 3 for Nearly Optimal Adaptive Procedure for Piecewise-Stationary Bandit: a Change-Point Detection Approach
Figure 4 for Nearly Optimal Adaptive Procedure for Piecewise-Stationary Bandit: a Change-Point Detection Approach

  Access Paper or Ask Questions

Stochastic Low-Rank Bandits


Dec 13, 2017
Branislav Kveton, Csaba Szepesvari, Anup Rao, Zheng Wen, Yasin Abbasi-Yadkori, S. Muthukrishnan

Figure 1 for Stochastic Low-Rank Bandits

  Access Paper or Ask Questions

A Tutorial on Thompson Sampling


Nov 19, 2017
Daniel Russo, Benjamin Van Roy, Abbas Kazerouni, Ian Osband, Zheng Wen

Figure 1 for A Tutorial on Thompson Sampling
Figure 2 for A Tutorial on Thompson Sampling
Figure 3 for A Tutorial on Thompson Sampling
Figure 4 for A Tutorial on Thompson Sampling

  Access Paper or Ask Questions

Online Learning to Rank in Stochastic Click Models


Jun 20, 2017
Masrour Zoghi, Tomas Tunys, Mohammad Ghavamzadeh, Branislav Kveton, Csaba Szepesvari, Zheng Wen

Figure 1 for Online Learning to Rank in Stochastic Click Models
Figure 2 for Online Learning to Rank in Stochastic Click Models
* Proceedings of the 34th International Conference on Machine Learning 
  Access Paper or Ask Questions

Does Weather Matter? Causal Analysis of TV Logs


Mar 24, 2017
Shi Zong, Branislav Kveton, Shlomo Berkovsky, Azin Ashkan, Nikos Vlassis, Zheng Wen

Figure 1 for Does Weather Matter? Causal Analysis of TV Logs
Figure 2 for Does Weather Matter? Causal Analysis of TV Logs
* Companion of the 26th International World Wide Web Conference 
  Access Paper or Ask Questions

Bernoulli Rank-$1$ Bandits for Click Feedback


Mar 19, 2017
Sumeet Katariya, Branislav Kveton, Csaba Szepesvári, Claire Vernade, Zheng Wen

Figure 1 for Bernoulli Rank-$1$ Bandits for Click Feedback
Figure 2 for Bernoulli Rank-$1$ Bandits for Click Feedback
Figure 3 for Bernoulli Rank-$1$ Bandits for Click Feedback

  Access Paper or Ask Questions