This cycle I am prioritizing recruiting post-docs, but I will still consider exceptional PhD student applications, particularly from candidates with prior research in learning theory or bandits/RL. If you emailed me and did not receive a response, I am sorry. My lack of reply is more a reflection of the amount of such emails I receive rather than a reflection of my enthusiasm for your candidacy. If you are a prospective PhD student, please submit your application through the regular system--I evaluate all applicants at the same time on the system. If you are applying for a post doc I try to reply to all candidates.
Post-docs: positions are for one year, with the potential for extension to a second year. To apply, please email me your CV, a link to your Google Scholar profile, and a couple of selected papers.
I am frequently asked about my current research interests. This is somewhat of a moving target, and my ideal situation is when a student pulls me in a direction I wouldn't naturally have entered myself. So if you're passionate about an area, try me! But my work tends to revolve around interactive machine learning. Some current interest areas are below.
An area I intend to grow in is sequential decision making problems with strategic or adversarial actors. A nonexhaustive list includes terms like online learning, multi-agent reinforcement learning, and learning in games. Some of my representative papers in this area (new for me, with more in the pipeline, ask me!):
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits, Arnab Maiti, Ross Boczar, Kevin Jamieson, Lillian J. Ratliff, AISTATS 2024. PDF
Logarithmic Regret for Matrix Games against an Adversary with Noisy Bandit Feedback, Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff, Preprint. PDF
Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners, Arnab Maiti, Junyan Liu, Kevin Jamieson, Lillian J. Ratliff, ICML 2026. PDF
Believe it or not, even in the single agent setting there still remain many fundamental gaps in the understanding of the sample complexity reinforcement learning. Some representative papers:
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning, Adhyyan Narang, Andrew Wagenmaker, Lillian Ratliff, Kevin Jamieson, NeurIPS 2024. PDF
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes, Cyrille Kone, Kevin Jamieson, AISTATS 2026. PDF
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs, Max Simchowitz, Kevin Jamieson, NeurIPS 2019. PDF
I am also interested in fundamental questions around the suprema of empirical processes and adaptive sampling. Some representative papers in this direction:
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits, Julian Katz-Samuels, Lalit Jain, Zohar Karnin, Kevin Jamieson, NeurIPS 2020. PDF
On the Power of Adaptivity for ε-Best Arm Identification in Linear Bandits, Arnab Maiti, Yunbei Xu, Kevin Jamieson, COLT 2026. PDF
Again, this is just a sample. If your area of choice isn't represented here but it's in the neighborhood, there is a fair chance I'd be excited to work on it with you. Good luck, and talk to you soon.