Abstract:We study high-probability regret bounds for online convex optimization (OCO) with strongly convex losses and establish three results that resolve open questions at the intersection of noise adaptivity, feedback structure, and constraint satisfaction. For the full-information setting with sub-Gaussian stochastic gradients, we prove a noise-adaptive high-probability regret bound in which the martingale deviation term scales with the noise level $\sigma$ rather than the gradient bound $G$, yielding a multiplicative improvement of $G/\sigma$ over the classical Azuma-Hoeffding baseline. Our analysis introduces an exponential supermartingale argument that bypasses the bounded-difference requirement of Freedman's inequality, enabling direct treatment of unbounded sub-Gaussian noise without truncation artifacts. For bandit feedback, we prove a minimax lower bound: the high-probability regret scales linearly in $\log(1/\delta)$, in contrast to the $\sqrt{\log(1/\delta)}$ confidence cost under full information. This constitutes a formal separation in the confidence cost of strongly convex OCO across feedback models. Regarding constrained OCO with stochastic constraints satisfying a Slater condition, we provide simultaneous high-probability guarantees for both cumulative regret and long-run constraint violation, achieving $\mathcal{O}(\sqrt{T\log(m/\delta)})$ regret and $\mathcal{O}(\sqrt{T}/(\zeta\delta) + m\sqrt{T\log(m/\delta)})$ violation. Synthetic experiments corroborate all theoretical predictions.
From: Wentao Zhang [view email]
[v1]
Sat, 6 Jun 2026 07:40:55 UTC (147 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。