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. 2102.03803
11
15

Lazy OCO: Online Convex Optimization on a Switching Budget

7 February 2021
Uri Sherman
Tomer Koren
ArXivPDFHTML
Abstract

We study a variant of online convex optimization where the player is permitted to switch decisions at most SSS times in expectation throughout TTT rounds. Similar problems have been addressed in prior work for the discrete decision set setting, and more recently in the continuous setting but only with an adaptive adversary. In this work, we aim to fill the gap and present computationally efficient algorithms in the more prevalent oblivious setting, establishing a regret bound of O(T/S)O(T/S)O(T/S) for general convex losses and O~(T/S2)\widetilde O(T/S^2)O(T/S2) for strongly convex losses. In addition, for stochastic i.i.d.~losses, we present a simple algorithm that performs log⁡T\log TlogT switches with only a multiplicative log⁡T\log TlogT factor overhead in its regret in both the general and strongly convex settings. Finally, we complement our algorithms with lower bounds that match our upper bounds in some of the cases we consider.

View on arXiv
Comments on this paper