Jeremy McMahan
Hi! I recently completed my PhD in Computer Science at the University of Wisconsin-Madison, where I was advised by Jerry Zhu and worked closely with Qiaomin Xie and Yudong Chen.
My research lies at the intersection of Approximation Algorithms, Reinforcement Learning Theory, and Algorithmic Game Theory — overcoming intractability barriers facing sequential decision-making under uncertainty. My algorithms enable near-optimal agents that provably obey safety constraints and operate robustly, even in NP-hard and adversarial domains.
More broadly, I am interested in principled ways to combine machine learning and worst-case algorithm design to ensure tractable and reliable AI decision-making.