Mark Sellke

Mark Sellke



[not mselke but] msellke [at] fas [dot] harvard [dot] edu


I am an Assistant Professor of Statistics at Harvard. I received my PhD in mathematics from Stanford, where I was fortunate to be advised by Andrea Montanari and Sébastien Bubeck. My research interests are a mix of probability and machine learning.

Spring 2024 Course: Random High-Dimensional Optimization: Landscapes and Algorithmic Barriers

Selected Papers

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

B. Huang and M. Sellke. A Constructive Proof of the Spherical Parisi Formula

M. Sellke. The Threshold Energy of Low Temperature Langevin Dynamics for Pure Spherical Spin Glasses

M. Sellke. Almost Quartic Lower Bound for the Fröhlich Polaron's Effective Mass via Gaussian Domination
Duke Math Journal, accepted (2023)

A. E. Alaoui, A. Montanari and M. Sellke. Sampling from the Sherrington-Kirkpatrick Gibbs measure via Algorithmic Stochastic Localization
FOCS 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, Vol. 70 (2023) no. 2, Article 10, 1-18
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. Chasing Convex Bodies Optimally
GAFA Seminar Notes, 2023
Conference version in SODA 2020. Awarded Best Paper and Best Student Paper.