Zheng Wen - Papers & Talks


In Progress

  • Z. Wen, E. Bax, and J. Li, "Revenue-Maximizing Mechanism Design for Quasi-Proportional Auctions", to be submitted . [arXiv Preprint]

  • P. Grigas, K. Lee, and Z. Wen, "Pro fit Maximization for Online Advertising Demand-Side Platforms", to be submitted.

  • Z. Wen, B. Kveton, M. Valko, and Sharan Vaswani, "Influence Maximization Semi-Bandits in Forests", submitted. [arXiv Preprint]

Journal Papers and Book Chapters

  • [J6] Z. Wen and B. Van Roy, "Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization", accepted by Mathematics of Operations Research. [arXiv Preprint]

  • [J5] B. Kveton, Z. Wen, A. Ashkan, and M. Valko, "Learning to Act Greedily: Polymatroid Semi-Bandits", accepted by Journal of Machine Learning Research, conditioned on minor revisions. [arXiv Preprint]

Peer Reviewed Conference Papers

  • [C18] S. Katariya, B. Kveton, C. Szepesvari, C. Vernade, and Z. Wen, "Stochastic Rank-1 Bandits", the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, 2017. [arXiv]

  • [C17] G. Theocharous, N. Vlassis, and Z. Wen, "An Interactive Points of Interest Guidance System", the 22nd Annual Meeting of the Intelligent User Interfaces Community (ACM IUI), Limassol, Cyprus, 2017.

  • [C3] Z. Wen, B. Kveton, B. Eriksson, and S. Bhamidipati, "Sequential Bayesian Search", International Conference on Machine Learning (ICML), Atlanta, Georgia, 2013. (acceptance rate: 24%)

Workshop Papers & Other Publication

  • [W4] S. Zong, B. Kveton, S. Berkovsky, A. Ashkan, N. Vlassis, and Z. Wen, "Does Weather Matter? Causal Analysis of TV Logs", poster at World Wide Web Conference (WWW), Perth, Western Australia, 2017. [arXiv Preprint]


  • [P2] Content-Adaptive Speed Adjusting Algorithm to Shorten Video, with Haojian Jin and Yale Song, US Patent App., filed, 2016. This patent was filed when I was at Yahoo Labs.

Selected Talks

  • Z. Wen and B. Van Roy, "Generalization and Exploration via Randomized Value Functions", INFORMS Annual Meeting 2014, San Francisco, CA.

  • Z. Wen and B. Van Roy, "Efficient Reinforcement Learning with Compact Value Function Approximations", INFORMS Annual Meeting 2013, Minneapolis, MN.

  • Z. Wen, B. Kveton, and S. Bhamidipati, "Learning to Discover: a Bayesian Approach", NIPS Workshop on Bayesian Optimization and Decision Making, Lake Tahoe, NV, December 2012.

  • Z. Wen and B. Van Roy, "Efficient Reinforcement Learning with Sparse Representations", INFORMS Annual Meeting 2012, Phoenix, AZ.

  • Z. Wen, H. Maei, and D. O'Neill, "Optimal Demand Response using Device Based Reinforcement Learning", INFORMS Annual Meeting 2012, Phoenix, AZ.

  • Z. Wen and B. Van Roy, "Efficient Reinforcement Learning", INFORMS Annual Meeting 2011, Charlotte, NC.

  • Z. Wen, K. Aziz, L. Durlofsky, and B. Van Roy, "Reservoir Management Based on Approximate Dynamic Programming", INFORMS Annual Meeting 2009, San Diego, CA.