Mark Sellke

Mark Sellke



[not mselke but] msellke [at] gmail [dot] com


I am a postdoc at Amazon. In Fall 2023 I will join the Department of Statistics at Harvard as an assistant professor. I received my Ph.D. in mathematics from Stanford, advised by Andrea Montanari and Sébastien Bubeck. My research interests are a mix of probability and machine learning.

Some Representative Papers

See my research page for a full list of papers, as well as some accompanying videos and slides.

M. Sellke. Almost Quartic Lower Bound for the Fröhlich Polaron's Effective Mass via Gaussian Domination.

A. E. Alaoui, A. Montanari and M. Sellke. Sampling from the Sherrington-Kirkpatrick Gibbs measure via Algorithmic Stochastic Localization.
FOCS 2022

A. Liu and M. Sellke. The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication.
COLT 2022

B. Huang and M. Sellke. Tight Lipschitz Hardness for Optimizing Mean Field Spin Glasses.
FOCS 2022

S. Bubeck and M. Sellke. A Universal Law of Robustness via Isoperimetry.
Journal of the ACM, accepted.
Conference version in NeurIPS 2021. Awarded Outstanding Paper.

M. Sellke. Cutoff for the Asymmetric Riffle Shuffle.
Annals of Probability, Vol. 50 (2022) no. 6, 2244-2287

M. Sellke and A. Slivkins. The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity.
Operations Research. Extended abstract in EC 2021.

A. E. Alaoui, A. Montanari and M. Sellke. Optimization of Mean-Field Spin Glasses.
Annals of Probability, Vol. 49 (2021) no. 6, 2922-2960

M. Sellke. Chasing Convex Bodies Optimally.
GAFA Seminar Notes.
Conference version in SODA 2020. Awarded Best Paper and Best Student Paper.