paper-with-me

홈 › Papers

Online Optimization on Hadamard Manifolds: Curvature Independent Regret Bounds on Horospherically Convex Objectives

2025-09-14 · Emre Sahinoglu, Shahin Shahrampour arxiv

We study online Riemannian optimization on Hadamard manifolds under the framework of horospherical convexity (h-convexity). Prior work mostly relies on the geodesic convexity (g-convexity), leading to regret bounds scaling poorly with the manifold curvature. To address this limitation, we analyze Riemannian online gradient descent for h-convex and strongly h-convex functions and establish $O(\sqrt{T})$ and $O(\log(T))$ regret guarantees, respectively. These bounds are curvature-independent and match the results in the Euclidean setting. We validate our approach with experiments on the manifold of symmetric positive definite (SPD) matrices equipped with the affine-invariant metric. In particular, we investigate online Tyler's $M$-estimation and online Fréchet mean computation, showing the application of h-convexity in practice.

📄 PDF Abstract BibTeX arXiv:2509.11236

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decentralized Online Riemannian Optimization Beyond Hadamard Manifolds

2025-09-09 · Emre Sahinoglu, Shahin Shahrampour arxiv

We study decentralized online Riemannian optimization over manifolds with possibly positive curvature, going beyond the Hadamard manifold setting. Decentralized optimization techniques rely on a consensus step that is we…

No-regret Online Learning over Riemannian Manifolds

2021-12-01 · NeurIPS 2021 12 · Xi Wang, Zhipeng Tu, Yiguang Hong, Yingyi Wu 외

We consider online optimization over Riemannian manifolds, where a learner attempts to minimize a sequence of time-varying loss functions defined on Riemannian manifolds. Though many Euclidean online convex optimization …

Implicit Riemannian Optimism with Applications to Min-Max Problems

2025-01-30 · Christophe Roux, David Martínez-Rubio, Sebastian Pokutta

We introduce a Riemannian optimistic online learning algorithm for Hadamard manifolds based on inexact implicit updates. Unlike prior work, our method can handle in-manifold constraints, and matches the best known regret…

Horoballs and the subgradient method

2024-03-23 · Adrian S. Lewis, Genaro Lopez-Acedo, Adriana Nicolae

To explore convex optimization on Hadamard spaces, we consider an iteration in the style of a subgradient algorithm. Traditionally, such methods assume that the underlying spaces are manifolds and that the objectives are…

First-order Methods for Geodesically Convex Optimization

2016-02-19 · Hongyi Zhang, Suvrit Sra

Geodesic convexity generalizes the notion of (vector space) convexity to nonlinear metric spaces. But unlike convex optimization, geodesically convex (g-convex) optimization is much less developed. In this paper we contr…