Skip to yearly menu bar Skip to main content


Poster

Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

Daniel Dodd · Louis Sharrock · Chris Nemeth

Hall C 4-9
[ ]
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

In recent years, interest in gradient-based optimization over Riemannian manifolds has surged. However, a significant challenge lies in the reliance on hyperparameters, especially the learning rate, which requires meticulous tuning by practitioners to ensure convergence at a suitable rate. In this work, we introduce innovative learning-rate-free algorithms for stochastic optimization over Riemannian manifolds, eliminating the need for hand-tuning and providing a more robust and user-friendly approach. We establish high probability convergence guarantees that are optimal, up to logarithmic factors, compared to the best-known optimally tuned rate in the deterministic setting. Our approach is validated through numerical experiments, demonstrating competitive performance against learning-rate-dependent algorithms.

Live content is unavailable. Log in and register to view live content