18
1

Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints

Abstract

We study the problem of online convex optimization (OCO) under unknown linear constraints that are either static, or stochastically time-varying. For this problem, we introduce an algorithm that we term Optimistically Safe OCO (OSOCO) and show that it enjoys O~(T)\tilde{\mathcal{O}}(\sqrt{T}) regret and no constraint violation. In the case of static linear constraints, this improves on the previous best known O~(T2/3)\tilde{\mathcal{O}}(T^{2/3}) regret with only slightly stronger assumptions. In the case of stochastic time-varying constraints, our work supplements existing results that show O(T)\mathcal{O}(\sqrt{T}) regret and O(T)\mathcal{O}(\sqrt{T}) cumulative violation under more general convex constraints albeit a less general feedback model. In addition to our theoretical guarantees, we also give numerical results comparing the performance of OSOCO to existing algorithms.

View on arXiv
Comments on this paper