Publications

You can also find my papers on my Google Scholar profile.

Journal Papers and Book Chapters.

• Optimal Auctions through Deep Learning: Advances in Differentiable Economics. (Alphabetical) Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, and Sai S. Ravindranath. Journal of the ACM, Volume 71, Issue 1, Article No.:5, pp 1-53, supercedes the previous ICML-19 and CACM versions.
• Machine Learning for Matching Markets. (Alphabetical) Zhe Feng, David C. Parkes, and Sai S. Ravindranath. Online and Matching-Based Market Design, Chapter 28, pp. 591-613, May 2023.
• Optimal Auctions through Deep Learning. (Alphabetical) Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, and Sai S. Ravindranath. Communications of the ACM, Volume 64, Issue 8, August 2021.
• Understanding PPA-Completeness. (Alphabetical) Xiaotie Deng, Jack R. Edmonds, Zhe Feng, Zhengyang Liu, Qi Qi, and Zeying Xu. Journal of Computer and System Sciences, 2021, supercedes the previous CCC-16 version.
• Machine Learning for Optimal Economic Design. (Alphabetical) Paul Dütting, Zhe Feng, Noah Golowich, Harikrishna Narasimhan, David C. Parkes, and Sai S. Ravindranath. The Future of Economic Design, pp 495-515, 2019.
• An Adaptive Independence Sampler MCMC Algorithm for Bayesian Inferences of Functions. Zhe Feng and Jinglai Li. SIAM Journal on Scientific Computing, 40(3), pp 1301-1321, 2018. arXiv.

Published Conference Papers.

• Auctions with LLM Summaries. (Alphabetical) Avinava Dubey, Zhe Feng, Rahul Kidambi, Aranyak Mehta and Di Wang. KDD-24 (to appear). arXiv.
• Joint Feedback Loop for Spend and Return-On-Spend Constraints. (Alphabetical) Santiago R. Balseiro, Kshipra Bhawalkar, Zhe Feng, Haihao Lu, Vahab Mirrokni, Balasubramanian Sivan, Di Wang. ICML-24 (to appear). arXiv.
• User Response in Ad Auctions: An MDP Formulation of Long-term Revenue Optimization. (Alphabetical) Yang Cai, Zhe Feng, Christopher Liaw, Aranyak Mehta and Grigoris Velegkas. TheWebConf-24. arXiv.
• Learning Thresholds with Latent Values and Censored Feedback. Jiahao Zhang, Tao Lin, Weiqiang Zheng, Zhe Feng, Yifeng Teng and Xiaotie Deng. ICLR-24 (to appear). arXiv.
• Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts. Chaoqi Wang, Ziyu Ye, Zhe Feng, Ashwinkumar Badanidiyuru and Haifeng Xu. NeurIPS-23 (Spotlight). arXiv.
• Pairwise Ranking Losses of Click-Through Rates Prediction for Welfare Maximization in Ad Auctions. Boxiang Lyu, Zhe Feng, Zachary Robertson and Oluwasanmi O Koyejo. ICML-23. arXiv.
• Improved Online Learning Algorithms for CTR Prediction in Ad Auctions. (Alphabetical) Zhe Feng, Christopher Liaw and Zixin Zhou. ICML-23. Conference Version.
• Learning to Bid in Contextual First Price Auctions. (Alphabetical) Ashwinkumar Badanidiyuru, Zhe Feng and Guru Guruganesh. TheWebConf-23. arXiv.
• Online Bidding Algorithms for Return-on-Spend Constrained Advertisers. (Alphabetical) Zhe Feng, Swati Padmanabhan, Di Wang. TheWebConf-23. arXiv.
• Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards. (Alphabetical) Ashwinkumar Badanidiyuru Varadaraja, Zhe Feng, Tianxi Li and Haifeng Xu. NeurIPS-22. arXiv.
• A Context-Integrated Transformer-Based Neural Network for Auction Design. Zhijian Duan, Jingwu Tang, Yutong Yin, Zhe Feng, Xiang Yan, Manzil Zaheer, and Xiaotie Deng. ICML-22. arXiv.
• Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning. Jibang Wu, Zixuan Zhang, Zhe Feng, Zhaoran Wang, Zhuoran Yang, Michael I. Jordan, Haifeng Xu. EC-22. arXiv.
• Welfare-Preserving $\varepsilon$-BIC to BIC Transformation with Negligible Revenue Loss. (Alphabetical) Vincent Conitzer, Zhe Feng, David C. Parkes, and Eric Sodomka. WINE-21. arXiv.
• Reserve Price Optimization for First Price Auctions in Display Advertising. Zhe Feng, Sebastien Lahaie, Jon Schneider, and Jinchao Ye. ICML-21 (Long Oral). arXiv.
• Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions. (Alphabetical) Zhe Feng, Guru Guruganesh, Christopher Liaw, Aranyak Mehta, and Abhishek Sethi. AAAI-21. arXiv.
• The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation. (Alphabetical) Zhe Feng, David C. Parkes, and Haifeng Xu. ICML-20. arXiv.
• Optimal Auctions through Deep Learning. (Alphabetical) Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C. Parkes, and Sai S. Ravindranath. ICML-19 (Long Oral). arXiv.
• Online Learning for Measuring Incentive Compatibility in Ad Auctions. Zhe Feng, Okke Schrijvers, and Eric Sodomka. TheWebConf-19. arXiv.
• Deep Learning for Revenue-Optimal Auctions with Budgets. Zhe Feng, Harikrishna Narasimhan, and David C. Parkes. AAMAS-18. Conference Version.
• Learning to Bid Without Knowing your Value. (Alphabetical) Zhe Feng, Chara Podimata, and Vasilis Syrgkanis. EC-18. arXiv.
• Power-Law Distributions in a Two-sided Market and Net Neutrality. (Alphabetical) Xiaotie Deng, Zhe Feng, and Christos H. Papadimitriou. WINE-16. arXiv.
• Understanding PPA-Completeness. (Alphabetical) Xiaotie Deng, Jack R. Edmonds, Zhe Feng, Zhengyang Liu, Qi Qi, and Zeying Xu. CCC-16. Conference Version.

Manuscript papers.

• Deep Learning for Two-Sided Matching. Sai S. Ravindranath, Zhe Feng, Shira Li, Jonathan Ma, Scott D. Kominers, David C. Parkes. arXiv.
• Robust Clearing Price Mechanisms for Reserve Price Optimization. Zhe Feng and Sebastien Lahaie. arXiv.