Austin J Stromme — accepted AI-conference papers

2025

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics

Omar Chehab, Anna Korba, Austin J Stromme, Adrien Vacher

ICLR 2025poster

Geometric tempering is a popular approach to sampling from challenging multi-modal probability distributions by instead sampling from a sequence of distributions which interpolate, using the geometric mean, between an easier proposal distribution and the target distribution. In this paper, we theore…

Cited by 3 Source ↗PDF ↗Scholar ↗

2021

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

Jason Altschuler, Sinho Chewi, Patrik Robert Gerber, Austin J Stromme

NeurIPS 2021spotlight

We study first-order optimization algorithms for computing the barycenter of Gaussian distributions with respect to the optimal transport metric. Although the objective is geodesically non-convex, Riemannian gradient descent empirically converges rapidly, in fact faster than off-the-shelf methods su…

Cited by 60 Source ↗PDF ↗Scholar ↗