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. 2206.11780
13
30

Chasing Convex Bodies and Functions with Black-Box Advice

23 June 2022
Nicolas H. Christianson
Tinashe Handina
Adam Wierman
ArXivPDFHTML
Abstract

We consider the problem of convex function chasing with black-box advice, where an online decision-maker aims to minimize the total cost of making and switching between decisions in a normed vector space, aided by black-box advice such as the decisions of a machine-learned algorithm. The decision-maker seeks cost comparable to the advice when it performs well, known as consistency\textit{consistency}consistency, while also ensuring worst-case robustness\textit{robustness}robustness even when the advice is adversarial. We first consider the common paradigm of algorithms that switch between the decisions of the advice and a competitive algorithm, showing that no algorithm in this class can improve upon 3-consistency while staying robust. We then propose two novel algorithms that bypass this limitation by exploiting the problem's convexity. The first, INTERP, achieves (2+ϵ)(\sqrt{2}+\epsilon)(2​+ϵ)-consistency and O(Cϵ2)\mathcal{O}(\frac{C}{\epsilon^2})O(ϵ2C​)-robustness for any ϵ>0\epsilon > 0ϵ>0, where CCC is the competitive ratio of an algorithm for convex function chasing or a subclass thereof. The second, BDINTERP, achieves (1+ϵ)(1+\epsilon)(1+ϵ)-consistency and O(CDϵ)\mathcal{O}(\frac{CD}{\epsilon})O(ϵCD​)-robustness when the problem has bounded diameter DDD. Further, we show that BDINTERP achieves near-optimal consistency-robustness trade-off for the special case where cost functions are α\alphaα-polyhedral.

View on arXiv
Comments on this paper