Austin J. Stromme

Google Scholar | CV

I am an assistant professor in the Statistics Department at ENSAE/CREST. I work at the high-dimensional intersection of optimization, geometry, and probability, and am particularly interested in statistical questions in optimal transport. Previously, I received my PhD from MIT EECS.

Online seminar on statistics and geometry

I am currently co-organizing an online seminar on statistics and geometry, please see the seminar homepage here. The aim is to promote communication between the two fields, and we encourage speakers to give synthetic and pedagogical talks of about one hour, aimed at a broad mathematical audience.

Papers

On the implicit regularization of Langevin dynamics with projected noise

Govind Menon, Austin J. Stromme, Adrien Vacher
arXiv preprint 2026

The ballistic limit of the log-Sobolev constant equals the Polyak-Łojasiewicz constant

Sinho Chewi, Austin J. Stromme
Annales de l'Institut Henri Poincaré (B) Probabilités et Statistiques, 2026+

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics

Omar Chehab, Anna Korba, Austin J. Stromme, Adrien Vacher
International Conference on Learning Representations (ICLR) 2025

On the sample complexity of entropic optimal transport

Philippe Rigollet, Austin J. Stromme
Annals of Statistics 2025

Minimum intrinsic dimension scaling for entropic optimal transport

Austin J. Stromme
Extended abstract in International Conference on Soft Methods in Probability and Statistics 2024, Best paper award

Sampling from a Schrödinger bridge

Austin J. Stromme
Conference on Artifical Intelligence and Statistics (AISTATS) 2023

Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space

Thibaut Le Gouic, Quentin Paris, Philippe Rigollet, Austin J. Stromme
Journal of the European Math Society (JEMS) 2022

Asymptotics for semi-discrete entropic optimal transport

Jason M. Altschuler, Jon Niles-Weed, Austin J. Stromme
SIAM Journal on Mathematical Analysis (SIMA) 2022

Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent

Jason M. Altschuler, Sinho Chewi, Patrik Gerber, Austin J. Stromme
Neural Information Processing Systems (NeurIPS) 2021 Spotlight presentation

Fast and Smooth Interpolation on Wasserstein Space

Sinho Chewi, Julien Clancy, Thibaut Le Gouic, Philippe Rigollet, George Stepaniants, Austin J. Stromme
Artificial Intelligence and Statistics (AISTATS) 2021

Exponential ergodicity of mirror-Langevin diffusions

Sinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu, Philippe Rigollet, Austin J. Stromme
Neural Information Processing Systems (NeurIPS) 2020

Gradient descent algorithms for Bures-Wasserstein barycenters

Sinho Chewi, Tyler Maunu, Philippe Rigollet, Austin J. Stromme
Conference on Learning Theory (COLT) 2020

Algebraic Properties of Generalized Graph Laplacians

David Jekel, Avi Levy, Will Dana, Austin Stromme, Collin Litterell
SIAM Journal of Discrete Math (SIDMA) 2018

Frog Model Wakeup Time on the Complete Graph

Nikki Carter, Brittany Dygert, Stephen Lacina, Collin Litterell, Austin Stromme, Andrew You
Rose-Hulman Undergraduate Math Journal 2016