Working Paper
Xiaotie Deng, Zhe Feng, and Rucha Kulkarni. Working Paper. “Octahedral Tucker is PPA-complete”. ECCC-TR17-118
In Press
Zhe Feng and Jinglai Li. In Press. “An adaptive independence sampler MCMC algorithm for infinite dimensional Bayesian inferences.” SIAM Journal on Scientific Computing. ArXiv
Zhe Feng, Chara Podimata, and Vasilis Syrgkanis. Submitted. “Learning to Bid Without Knowing your Value.” Preliminary version appears in Workshop on Learning in the Presence of Strategic Behavior, NIPS'17. ArXiv
Paul Duetting, Zhe Feng, Harikrishna Narasimhan, and David C. Parkes. Submitted. “Optimal Auctions through Deep Learning.” Preliminary version appears in 3rd Workshop on Algorithmic Game Theory and Data Science, EC'17. ArXiv
Zhe Feng, Harikrishna Narasimhan, and David C. Parkes. 7/2018. “Deep Learning for Revenue-Optimal Auctions with budgets.” To appear in the proceedings of 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2018).
Xiaotie Deng, Zhe Feng, and Christos H. Papadimitriou. 12/2016. “Power-Law Distributions in a Two-sided Market and Net Neutrality.” The Proceedings of 12th Conference on Web and Internet Economics (WINE 2016) 10123, Pp. 59-72. Montreal, Canada. ArXiv PPT
Xiaotie Deng, Jack R. Edmonds, Zhe Feng, Zhengyang Liu, Qi Qi, and Zeying Xu. 6/2016. “Understanding PPA-Completeness.” The Proceedings of 31st Computational Complexity Conference (CCC 2016) 50, Pp. 23:1--23:25. Tokyo, Japan. PDF