Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

Dodd, Daniel and Sharrock, Louis and Nemeth, Christopher (2024) Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds. Proceedings of Machine Learning Research. ISSN 1938-7228 (In Press)

Text (riemannian_dog_icml) - Accepted Version
Available under License Creative Commons Attribution.
Download (0B)

Text (riemannian_dog_icml) - Accepted Version
Available under License Creative Commons Attribution.
Download (0B)

Text (riemannian_dog_icml) - Accepted Version
Available under License Creative Commons Attribution.
Download (0B)

Text (riemannian_dog_icml) - Accepted Version
Available under License Creative Commons Attribution.
Download (0B)

Text (riemannian_dog_icml) - Accepted Version
Available under License Creative Commons Attribution.
Download (0B)

Text (riemannian_dog_icml)
riemannian_dog_icml.pdf - Accepted Version
Available under License Creative Commons Attribution.
Download (8MB)

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.