Jiantao Jiao

I am an Assistant Professor in the Department of Electrical Engineering and Computer Sciences and Department of Statistics at University of California, Berkeley. I received the Ph.D. degree from Stanford University in 2018. I am a member of the Berkeley Laboratory of Information and System Sciences (BLISS) and the Berkeley Artificial Intelligence Research (BAIR) Lab. I am broadly interested in statistical machine learning, mathematical data science, optimization, applied probability, information theory, and their applications in science and engineering. Recently, my research has been focusing on the theory and system of robust learning, (inverse) reinforcement learning, the interplay between economics, statistics, and computation, and distributed (permissionless) systems.

Recent publications

• Provably Breaking the Quadratic Error Compounding Barrier in Imitation Learning, Optimally
  Nived Rajaraman, Yanjun Han, Lin F. Yang, Kannan Ramchandran, Jiantao Jiao

• Minimax Off-Policy Evaluation for Multi-Armed Bandits
  Cong Ma, Banghua Zhu, Jiantao Jiao, Martin J. Wainwright

• Toward the Fundamental Limits of Imitation Learning
  Nived Rajaraman, Lin F. Yang, Jiantao Jiao, Kannan Ramchandran, NeurIPS 2020

• SLIP: Learning to Predict in Unknown Dynamical Systems with Long-Term Memory
  Paria Rashidinejad, Jiantao Jiao, Stuart Russell, NeurIPS 2020 (Oral)

• Robust Estimation via Generalized Quasi-gradients
  Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

• Generalized Resilience and Robust Statistics
  Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

• Minimax Estimation of Divergences between Discrete Distributions
  Yanjun Han, Jiantao Jiao, Tsachy Weissman

• Optimal Rates of Entropy Estimation over Lipschitz Balls
  Yanjun Han, Jiantao Jiao, Tsachy Weissman, Yihong Wu, Annals of Statistics

• Theoretically Principled Trade-off between Robustness and Accuracy
  Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan, ICML, 2019

• The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal
  Jiantao Jiao, Weihao Gao, Yanjun Han, NeurIPS 2018 (Spotlight)

• Entropy Rate Estimation for Markov Chains with Large State Space
  Yanjun Han, Jiantao Jiao, Chuan-Zheng Lee, Tsachy Weissman, Yihong Wu, Tiancheng Yu, NeurIPS 2018 (Spotlight)

Contact

University of California, Berkeley

Department of Electrical Engineering and Computer Sciences

257M Cory Hall

Berkeley, CA 94720-1770

Email: jiantao [at] eecs [dot] berkeley [dot] edu