English

Online Convex Optimization with Perturbed Constraints

Optimization and Control 2019-06-04 v1

Abstract

This paper addresses Online Convex Optimization (OCO) problems where the constraints have additive perturbations that (i) vary over time and (ii) are not known at the time to make a decision. Perturbations may not be i.i.d. generated and can be used to model a time-varying budget or commodity in resource allocation problems. The problem is to design a policy that obtains sublinear regret while ensuring that the constraints are satisfied on average. To solve this problem, we present a primal-dual proximal gradient algorithm that has O(TϵT1ϵ)O(T^\epsilon \vee T^{1-\epsilon}) regret and O(Tϵ)O(T^\epsilon) constraint violation, where ϵ[0,1)\epsilon \in [0,1) is a parameter in the learning rate. Our results match the bounds of previous work on OCO with time-varying constraints when ϵ=1/2\epsilon = 1/2; however, we (i) define the regret using a time-varying set of best fixed decisions; (ii) can balance between regret and constraint violation; and (iii) use an adaptive learning rate that allows us to run the algorithm for any time horizon.

Keywords

Cite

@article{arxiv.1906.00049,
  title  = {Online Convex Optimization with Perturbed Constraints},
  author = {Víctor Valls and George Iosifidis and Douglas J. Leith and Leandros Tassiulas},
  journal= {arXiv preprint arXiv:1906.00049},
  year   = {2019}
}
R2 v1 2026-06-23T09:36:02.681Z