arXiv Machine Learning
$\tilde{O}(\sqrt{T})$ Regret and Polylogarithmic Constraint Violation for COCO
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
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 27
BAGEL: Adversarially Constrained Online Convex Optimization under Separation Oracle Access
arXiv:2502. 16744v3 Announce Type: replace Abstract: In adversarial Constrained Online Convex Optimization (COCO), a learner selects actions from a fixed convex set while seeking both low regret and low cumulative constraint violation (CCV) under time-varying constraints.
arXiv AI
Sep 10
Constrained Online Learning with Noisy Constraint Values
arXiv:2609. 06921v1 Announce Type: cross Abstract: We study constrained online convex optimization with adversarial constraints when constraint values and gradients are observed through unbiased noise.
arXiv Machine Learning
Jul 14
Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
arXiv:2607. 10808v1 Announce Type: new Abstract: The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action $x_t \in \mathcal{X} \subset \mathbb{R}^d$, a convex loss function $f_t$ and a convex constraint function $g_t$ that drives the constraint $g_t(x)\le 0$ are revealed.
arXiv Machine Learning
Jul 23
Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence
arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.
arXiv Machine Learning
Jul 13
Logarithmic High-Probability Regret for Online Convex Optimization with Two-Point Bandit Feedback
arXiv:2603. 25029v4 Announce Type: replace Abstract: We study online convex optimization (OCO) with two-point bandit feedback against a non-anticipating adaptive adversary.