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.

  2. Computing Game Symmetries and Equilibria That Respect Them
    Emanuel Tewolde, Brian Hu Zhang, Caspar Oesterheld, Tuomas Sandholm, Vincent Conitzer
    AAAI 2025

  3. A Lower Bound on Swap Regret in Extensive-Form Games
    (αβ) Constantinos Daskalakis, Gabriele Farina, Noah Golowich, Tuomas Sandholm, Brian Hu Zhang
    arXiv 2024

  4. 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)

  5. Efficient Φ-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
    Brian Hu Zhang, Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm
    NeurIPS 2024

  6. Exponential Lower Bounds on the Double Oracle Algorithm in Zero-Sum Games
    Brian Hu Zhang, Tuomas Sandholm
    IJCAI 2024

  7. 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

  8. Hidden-Role Games: Equilibrium Concepts and Computation
    Luca Carminati*, Brian Hu Zhang*, Gabriele Farina, Nicola Gatti, Tuomas Sandholm
    EC 2024

  9. 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

  10. Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Extensive-Form Games
    Brian Hu Zhang, Gabriele Farina, Tuomas Sandholm
    ICLR 2024

  11. On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria
    Brian Hu Zhang, Tuomas Sandholm
    AAAI 2024

  12. 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

  13. Subgame Solving in Adversarial Team Games
    Brian Hu Zhang*, Luca Carminati*, Federico Cacciamani, Gabriele Farina, Pierriccardo Olivieri, Nicola Gatti, Tuomas Sandholm
    NeurIPS 2022

  14. Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games
    Brian Hu Zhang, Tuomas Sandholm
    NeurIPS 2022

  15. 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)

  16. 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

  17. 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

  18. Team Correlated Equilibria in Zero-Sum Extensive-Form Games via Tree Decompositions
    Brian Hu Zhang, Tuomas Sandholm
    AAAI 2022

  19. Subgame solving without common knowledge
    Brian Hu Zhang, Tuomas Sandholm
    NeurIPS 2021 Spotlight; AAAI Workshop on Reinforcement Learning in Games 2022 Oral Presentation

  20. 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

  21. Small Nash Equilibrium Certificates in Very Large Games
    Brian Hu Zhang, Tuomas Sandholm
    NeurIPS 2020

  22. Sparsified Linear Programming for Zero-Sum Equilibrium Finding
    Brian Hu Zhang, Tuomas Sandholm
    ICML 2020

  23. A Spectral View of Adversarially Robust Features
    Shivam Garg, Vatsal Sharan*, Brian Hu Zhang*, Gregory Valiant
    NeurIPS 2018 Spotlight

  24. Mitigating Unwanted Biases with Adversarial Learning
    Brian Hu Zhang, Blake Lemoine, Margaret Mitchell
    AIES 2018

  25. 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

Teaching

Carnegie Mellon University

Stanford University