Research

Interests

I use theory tools to design algorithms with provable guarantees for combinatorial problems, often with uncertain inputs. Many problems I work on arise from operations research and machine learning applications, including those with constraints, sequential decision-making, and multiple agents. I am also interested in how Psychology and Social Science can lead us to new algorithmic insights. A few of my favorite topics are below.

Classical Algorithms

Algorithms and Uncertainty

Publications
2024

Anytime-Constrained Multi-Agent Reinforcement Learning
Jeremy McMahan and Xiaojin Zhu
Preprint

Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time
Jeremy McMahan
Neurips 2024

Inception: Efficiently Computable Misinformation Attacks on Markov Games
Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, and Qiaomin Xie
RLC 2024

Roping in Uncertainty: Robustness and Regularization in Markov Games
Jeremy McMahan, Giovanni Artiglio, and Qiaomin Xie
ICML 2024

Minimally Modifying a Markov Game to Achieve any Nash Equilibrium and Value
Young Wu, Jeremy McMahan, Yiding Chen, Yudong Chen, Xiaojin Zhu, and Qiaomin Xie
ICML 2024

Anytime-Constrained Reinforcement Learning
Jeremy McMahan and Xiaojin Zhu
AISTATS 2024

Optimal Attack and Defense for Reinforcement Learning
Jeremy McMahan, Young Wu, Xiaojin Zhu, and Qiaomin Xie
AAAI 2024

Data Poisoning to Fake a Nash Equilibrium for Markov Games
Young Wu, Jeremy McMahan, Xiaojin Zhu, and Qiaomin Xie
AAAI 2024

2023

Approximating Pandora’s Box with Correlations
*Shuchi Chawla, *Evangelia Gergatsouli, *Jeremy McMahan, and *Christos Tzamos
APPROX 2023

Various Misleading Visual Features in Misleading Graphs: Do they truly deceive us?
Jihyun Rho, Martina A Rau, Shubham Kumar Bharti, Rosanne Luu, Jeremy McMahan, Andrew Wang, and Jerry Zhu
COGSCI 2023

VISER: A Tractable Solution Concept for Games with Information Asymmetry
Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, and Qiaomin Xie
Preprint

Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning
Young Wu, Jeremy McMahan, Xiaojin Zhu, and Qiaomin Xie
AAAI 2023

2021

A D-competitive Algorithm for the Multilevel Aggregation Problem with Deadlines
Jeremy McMahan
Preprint

Noble Deceit: Optimizing Social Welfare for Myopic Multi-Armed Bandits
*Ashwin Maran, *Jeremy McMahan, and *Nathaniel Sauerberg
GAMES 2020