arXiv Machine Learning
Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 27
Minimax Alternating Regret for the Experts Problem and Online Convex Optimization
arXiv:2608. 25182v1 Announce Type: cross Abstract: In this paper, we study alternating regret in online convex optimization (OCO), motivated by the success of alternating learning dynamics in two-player games.
arXiv Machine Learning
Jul 15
A Geometric Approach to Constrained Online Learning
arXiv:2605. 21107v2 Announce Type: replace Abstract: We study constrained online convex optimization with adversarial time-varying constraints.
arXiv Machine Learning
Aug 21
The Price of Hidden Curvature: Improved Lower Bounds for Bandit Convex Optimization
arXiv:2607. 18652v3 Announce Type: replace-cross Abstract: We establish improved lower bounds on the minimax expected regret of stochastic bandit convex optimization for $1$-Lipschitz functions on the $d$-dimensional Euclidean ball.
arXiv Machine Learning
Oct 3
Sharp Oracle-Regret Tradeoffs for Projection-Free Online Convex Optimization
The paper studies online convex optimization when the learner can only query an exact linear optimization oracle. It establishes a dimension‑free minimax expected regret bound of θ(GD max{√T, T/(1+min{Q,BT})^{1/4}}) for convex G‑Lipschitz losses, where Q is the total oracle budget and B the per‑round limit. The authors provide matching lower and upper bounds, showing how strict per‑round or total‑budget constraints affect the achievable regret, and extend the analysis to smooth losses with curvature‑dependent bounds.
Hugging Face Trending Papers
Jul 21
The Price of Hidden Curvature: An $\widetildeΩ (d^{5/4} \sqrt{T})$ Lower Bound for Bandit Convex Optimization
We establish a $\widetildeΩ(d^{5/4}\sqrt T)$ lower bound on the minimax expected regret of stochastic bandit convex optimization of $1$-Lipschitz functions on the Euclidean ball. This presents the first nontrivial regret lower bound that grows faster than $d\sqrt{T}$ for this problem, establishing that stochastic bandit convex optimization is fundamentally harder than linear bandits.
arXiv AI
Sep 10
Parameter-Free Dynamic Regret under Heavy-Tailed Noise
arXiv:2607. 27073v2 Announce Type: replace-cross Abstract: We study online convex optimization with stochastic gradient noise whose conditional $p$-th central moment is bounded by $\sigma^p$, for an unknown $p\in(1,2]$.