E-mail: bhzhang at cs dot cmu dot edu
Office: GHC 9225
CV, Google Scholar

I am a third-year PhD student in the Computer Science Department at Carnegie Mellon University, where I am fortunate to be advised by Tuomas Sandholm. Prior to CMU, I completed my undergraduate and master’s degrees at Stanford University, where I worked with Greg Valiant.

My current research interests lie in computational game theory, especially equilibrium-finding in large games. I have also done work in adversarial robustness, fairness in machine learning, and quantum computing.

Publications

“with” denotes alphabetical ordering of authors. * denotes equal contribution.

  2. Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games
    Brian Hu Zhang and Tuomas Sandholm
    arXiv preprint 2022

  3. 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 and Tuomas Sandholm
    EC 2022

  4. Team Belief DAG: A Concise Representation for Team-Correlated Game-Theoretic Decision Making
    Brian Hu Zhang, Gabriele Farina, and Tuomas Sandholm
    arXiv preprint 2022 and ICLR Workshop on Gamification and Multiagent Solutions 2022

  5. Polynomial-Time Sum-of-Squares Can Robustly Estimate Mean and Covariance of Gaussians Optimally
    with Pravesh K. Kothari and Peter Manohar
    ALT 2022

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

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

  8. Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games
    Brian Hu Zhang and Tuomas Sandholm
    AAAI 2021 and AAAI Workshop on Reinforcement Learning in Games 2021 Oral Presentation

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

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

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

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

  13. Advantages of Unfair Quantum Ground-State Sampling
    Brian Hu Zhang, Gene Wagenbreth, Victor Martin-Mayor, and Itay Hen
    Scientific Reports 2016

Teaching and Service

Service

Teaching Assistanceships

Stanford University