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. 2106.05165
18
10

A Lyapunov-Based Methodology for Constrained Optimization with Bandit Feedback

9 June 2021
Semih Cayci
Yilin Zheng
A. Eryilmaz
ArXivPDFHTML
Abstract

In a wide variety of applications including online advertising, contractual hiring, and wireless scheduling, the controller is constrained by a stringent budget constraint on the available resources, which are consumed in a random amount by each action, and a stochastic feasibility constraint that may impose important operational limitations on decision-making. In this work, we consider a general model to address such problems, where each action returns a random reward, cost, and penalty from an unknown joint distribution, and the decision-maker aims to maximize the total reward under a budget constraint BBB on the total cost and a stochastic constraint on the time-average penalty. We propose a novel low-complexity algorithm based on Lyapunov optimization methodology, named LyOn{\tt LyOn}LyOn, and prove that for KKK arms it achieves O(KBlog⁡B)O(\sqrt{K B\log B})O(KBlogB​) regret and zero constraint-violation when BBB is sufficiently large. The low computational cost and sharp performance bounds of LyOn{\tt LyOn}LyOn suggest that Lyapunov-based algorithm design methodology can be effective in solving constrained bandit optimization problems.

View on arXiv
Comments on this paper