ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2402.08799
9
3

Projection-Free Online Convex Optimization with Time-Varying Constraints

13 February 2024
Dan Garber
Ben Kretzu
ArXivPDFHTML
Abstract

We consider the setting of online convex optimization with adversarial time-varying constraints in which actions must be feasible w.r.t. a fixed constraint set, and are also required on average to approximately satisfy additional time-varying constraints. Motivated by scenarios in which the fixed feasible set (hard constraint) is difficult to project on, we consider projection-free algorithms that access this set only through a linear optimization oracle (LOO). We present an algorithm that, on a sequence of length TTT and using overall TTT calls to the LOO, guarantees O~(T3/4)\tilde{O}(T^{3/4})O~(T3/4) regret w.r.t. the losses and O(T7/8)O(T^{7/8})O(T7/8) constraints violation (ignoring all quantities except for TTT) . In particular, these bounds hold w.r.t. any interval of the sequence. We also present a more efficient algorithm that requires only first-order oracle access to the soft constraints and achieves similar bounds w.r.t. the entire sequence. We extend the latter to the setting of bandit feedback and obtain similar bounds (as a function of TTT) in expectation.

View on arXiv
Comments on this paper