AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

No-regret Online Learning over Riemannian Manifolds

Xi Wang, Zhipeng Tu, Yiguang Hong, Yingyi Wu, Guodong Shi

NeurIPS 2021 · Bandits and online learning › Online convex optimization and games · approach: Constrained and unconstrained OCO algorithms · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use strongly g-convex step size alpha_t = 1/(2t) instead of the convex step size (ablation)R-OGD · Frechet mean on SPD manifold, [n,N,T]=[100,10,1000]average regret R(t)/tImproved
Use bandit feedback R-BAN with one function value instead of two-point R-OZOR-BAN · Frechet mean in hyperbolic space, [n,N,T]=[100,10,10000], 100 runsaverage regretNo clear effect
Use R-OGD with step size D/(L sqrt(zeta T)) for g-convex losses on Hadamard manifoldsR-OGD · Regret bound theoryregretImproved
Use step size 1/(mu t) for mu-strongly g-convex lossesR-OGD · Regret bound theoryregretImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy