SOURCE-LINKED INTELLIGENCE

Constrained Online Learning with Noisy Constraint Values

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

We study constrained online convex optimization with adversarial constraints and conditionally unbiased, finite-variance observations of constraint values and gradients. Under common feasibility, our \LEDGER\ algorithm attains $O(\sqrt T)$ expected regret and $O(\sqrt{T\log(eT)})$ expected budget violation, the largest cumulative overspend over any window. It uses a reflected exponential potential, clipped signed observations, and predictable adaptive regularization, with one feedback triple and one projection per round. Neither a Slater condition, independence between feedback channels, nor a

Read original source ↗ Open in workspace

recordType

paper

region

Global