ICLR 2026poster0 citations

Adaptive gradient descent on Riemannian manifolds and its applications to Gaussian variational inference

Jiyoung Park, Jaewook J. Suh, Bofan Wang, Anirban Bhattacharya, Shiqian Ma

Abstract

We propose RAdaGD, a novel family of adaptive gradient descent methods on general Riemannian manifolds. RAdaGD adapts the step size parameter without line search, and includes instances that achieve a non-ergodic convergence guarantee, $f(x_k) - f(x_\star) \le \mathcal{O}(1/k)$, under local geodesic smoothness and generalized geodesic convexity. A core application of RAdaGD is Gaussian Variational Inference, where our method provides the first convergence guarantee in the absence of $L$-smoothness of the target log-density, under additional technical assumptions. We also investigate the empirical performance of RAdaGD in numerical simulations and demonstrate its competitiveness in comparison to existing algorithms.

Adaptive methodRiemannian optimizationVariational Inference
BibTeX
@inproceedings{
park2026adaptive,
title={Adaptive gradient descent on Riemannian manifolds and its applications to Gaussian variational inference},
author={Jiyoung Park and Jaewook J. Suh and Bofan Wang and Anirban Bhattacharya and Shiqian Ma},
booktitle={The Fourteenth International Conference on Learning Representations},
year={2026},
url={https://openreview.net/forum?id=2TTQjRkgFn}
}
Adaptive gradient descent on Riemannian manifolds and its applications to Gaussian variational inference · ICLR 2026