E-mail: bhzhang at cs dot cmu dot edu
Office: GHC 9231 9011
CV, Google Scholar
I am a PhD student in the Computer Science Department at Carnegie Mellon University, where I am fortunate to be advised by Prof. Tuomas Sandholm. I am supported by the CMU Hans J. Berliner Graduate Fellowship in Artificial Intelligence. I am on the academic job market this cycle!
My current research interests lie in computational game theory, especially equilibrium computation in extensive-form games; subgame solving; no-regret learning in games; automated mechanism design; adversarial team games; and solution concepts involving correlation, communication, and/or mediation. I have also done work in adversarial robustness, fairness in machine learning, and quantum computing.
Prior to CMU, I completed my undergraduate and master’s degrees at Stanford University, where I completed my honors thesis with Prof. Gregory Valiant.
Publications
(αβ) denotes alphabetical ordering of authors.
* denotes equal contribution.
-
Computing Game Symmetries and Equilibria That Respect Them
Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Tuomas Sandholm, Vincent Conitzer
AAAI 2025 -
A Lower Bound on Swap Regret in Extensive-Form Games
(αβ) Constantinos Daskalakis, Gabriele Farina, Noah Golowich, Tuomas Sandholm, Brian Hu Zhang
arXiv 2024 -
Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
Brian Hu Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm
Accepted to Mathematics of Operations Research 2024
Extended version of [11] (EC 2022) -
Efficient Φ-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
Brian Hu Zhang, Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm
NeurIPS 2024 -
Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games
Brian Hu Zhang, Tuomas Sandholm
IJCAI 2024 -
Imperfect-Recall Games: Equilibrium Concepts and Their Complexity
Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Manolis Zampetakis, Tuomas Sandholm, Paul W. Goldberg, Vincent Conitzer
IJCAI 2024 -
Hidden-Role Games: Equilibrium Concepts and Computation
Luca Carminati*, Brian Hu Zhang*, Gabriele Farina, Nicola Gatti, Tuomas Sandholm
EC 2024 -
Steering No-Regret Learners to a Desired Equilibrium
Brian Hu Zhang*, Gabriele Farina*, Ioannis Anagnostides, Federico Cacciamani, Stephen McAleer, Andreas Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm
EC 2024 -
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Extensive-Form Games
Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm
ICLR 2024 -
On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria
Brian Hu Zhang, Tuomas Sandholm
AAAI 2024 -
Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games
Brian Hu Zhang*, Gabriele Farina*, Ioannis Anagnostides, Federico Cacciamani, Stephen McAleer, Andreas Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm
NeurIPS 2023 -
Subgame Solving in Adversarial Team Games
Brian Hu Zhang*, Luca Carminati*, Federico Cacciamani, Gabriele Farina, Pierriccardo Olivieri, Nicola Gatti, Tuomas Sandholm
NeurIPS 2022 -
Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games
Brian Hu Zhang, Tuomas Sandholm
NeurIPS 2022 -
Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation
Brian Hu Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm
EC 2022
Extended by [22] (Mathematics of Operation Research 2024) -
Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization
Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm
ICML 2023
Earlier version presented at ICLR Workshop on Gamification and Multiagent Solutions (GMAS) 2022 -
Polynomial-Time Sum-of-Squares Can Robustly Estimate Mean and Covariance of Gaussians Optimally
(αβ) Pravesh K. Kothari, Peter Manohar, Brian Hu Zhang
ALT 2022 -
Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions
Brian Hu Zhang, Tuomas Sandholm
AAAI 2022 -
Subgame solving without common knowledge
Brian Hu Zhang, Tuomas Sandholm
NeurIPS 2021 Spotlight; AAAI Workshop on Reinforcement Learning in Games 2022 Oral Presentation -
Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games
Brian Hu Zhang, Tuomas Sandholm
AAAI 2021; AAAI Workshop on Reinforcement Learning in Games 2021 Oral Presentation -
Small Nash Equilibrium Certificates in Very Large Games
Brian Hu Zhang, Tuomas Sandholm
NeurIPS 2020 -
Sparsified Linear Programming for Zero-Sum Equilibrium Finding
Brian Hu Zhang, Tuomas Sandholm
ICML 2020 -
A Spectral View of Adversarially Robust Features
Shivam Garg, Vatsal Sharan*, Brian Hu Zhang*, Gregory Valiant
NeurIPS 2018 Spotlight -
Mitigating Unwanted Biases with Adversarial Learning
Brian Hu Zhang, Blake Lemoine, Margaret Mitchell
AIES 2018 -
Advantages of Unfair Quantum Ground-State Sampling
Brian Hu Zhang, Gene Wagenbreth, Victor Martin-Mayor, Itay Hen
Nature Scientific Reports 2016
Teaching and Service
Service
- Peer Review:
- AAAI: 2021–present
- NeurIPS: 2021–present
- ICLR: 2022–present
- ICML: 2022–present
- Journals: JAIR, IEEE TAI, Knowledge-Based Systems, Intl J Approximate Reasoning
- Workshops: AAAI Reinforcement Learning in Games
- CMU Theory Lunch Organizer, with Magdalen Dobson (Spring) & Praneeth Kacham (Fall), 2021
Teaching
Carnegie Mellon University
- Co-instructor, 15-888 Computational Game Solving, Fall 2024
- Teaching Assistant, 15-780 Graduate Artificial Intelligence, Spring 2023
Stanford University
- Teaching Assistant, CS 161 Design and Analysis of Algorithms, Winter 2019
- Teaching Assistant, CS 227B General Game Playing, Spring 2017–2019
- Section Leader, CS 106A Programming Methodology, Spring–Summer 2016
- Section Leader, CS 106B Programming Abstractions, Fall 2016–Winter 2017