Banghua Zhu

alt text 

Electrical Engineering and Computer Science Department,
University of California, Berkeley (UCB)
264 Cory Hall
Berkeley, California
Email: my first name My Google Scholar Page

About me

I received the B.S. degree in electronic engineering from Tsinghua University. I'm currently working as a fourth year Ph.D. student, advised by Prof. Jiantao Jiao and Prof. Michael I. Jordan. I was also very fortunate to work with Prof. Jacob Steinhardt, Prof. Martin Wainwright and Prof. David Tse.


My research interests are mainly on the fundamental problems in statistics, machine learning, mechanism design and security. In particular, I would like to deepen the understanding of the fundamental limit in robust statistics, distributed statistical inference, reinforcement learning and mechanism design.

Selected Papers

1. Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Paria Rashidinejad, Banghua Zhu, Cong Ma, Jiantao Jiao, Stuart Russell

In submission.

2. Minimax Off-Policy Evaluation for Multi-Armed Bandits

Cong Ma, Banghua Zhu, Jiantao Jiao, Martin J. Wainwright

In submission.

3.Robust estimation via generalized quasi-gradients

Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

Information and Inference: A Journal of the IMA

4.When does the Tukey Median work?

Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

ISIT 2020.

5. Generalized Resilience and Robust Statistics

Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

In submission.

6. Deconstructing Generative Adversarial Networks

Banghua Zhu, Jiantao Jiao, David Tse

IEEE Transactions on Information Theory.

Teaching and Services

1. Journal review: Bernoulli, Journal of the American Statistical Association, Information and Inference: A Journal of the IMA, IEEE Transactions on Information Theory´╝î IEEE Transactions on Signal Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Journal on Selected Areas in Communication,

2. Conference review: NeurIPS, ICML, ISIT

3. Teaching Assistant: EE 126 Spring 2020, DATA 102 Fall 2020