Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds

Download

• Paper
• arXiv
• Code

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.

Citation

Dodd, D., Sharrock, L. and Nemeth, C., Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds. In Forty-first International Conference on Machine Learning.

@inproceedings{doddlearning,
  title={Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds},
  author={Dodd, Daniel and Sharrock, Louis and Nemeth, Christopher},
  booktitle={Forty-first International Conference on Machine Learning}
}