Testing the Feasibility of Linear Programs with Bandit Feedback

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gangrade, Aditya, Gopalan, Aditya, Saligrama, Venkatesh, Scott, Clayton
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914845004136448
author Gangrade, Aditya
Gopalan, Aditya
Saligrama, Venkatesh
Scott, Clayton
author_facet Gangrade, Aditya
Gopalan, Aditya
Saligrama, Venkatesh
Scott, Clayton
contents While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem. We initiate the study of testing such feasibility assumptions, and in particular address the problem in the linear bandit setting, thus characterising the costs of feasibility testing for an unknown linear program using bandit feedback. Concretely, we test if $\exists x: Ax \ge 0$ for an unknown $A \in \mathbb{R}^{m \times d}$, by playing a sequence of actions $x_t\in \mathbb{R}^d$, and observing $Ax_t + \mathrm{noise}$ in response. By identifying the hypothesis as determining the sign of the value of a minimax game, we construct a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms. We prove that this test is reliable, and adapts to the `signal level,' $Γ,$ of any instance, with mean sample costs scaling as $\widetilde{O}(d^2/Γ^2)$. We complement this by a minimax lower bound of $Ω(d/Γ^2)$ for sample costs of reliable tests, dominating prior asymptotic lower bounds by capturing the dependence on $d$, and thus elucidating a basic insight missing in the extant literature on such problems.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15648
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Testing the Feasibility of Linear Programs with Bandit Feedback
Gangrade, Aditya
Gopalan, Aditya
Saligrama, Venkatesh
Scott, Clayton
Machine Learning
Statistics Theory
While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem. We initiate the study of testing such feasibility assumptions, and in particular address the problem in the linear bandit setting, thus characterising the costs of feasibility testing for an unknown linear program using bandit feedback. Concretely, we test if $\exists x: Ax \ge 0$ for an unknown $A \in \mathbb{R}^{m \times d}$, by playing a sequence of actions $x_t\in \mathbb{R}^d$, and observing $Ax_t + \mathrm{noise}$ in response. By identifying the hypothesis as determining the sign of the value of a minimax game, we construct a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms. We prove that this test is reliable, and adapts to the `signal level,' $Γ,$ of any instance, with mean sample costs scaling as $\widetilde{O}(d^2/Γ^2)$. We complement this by a minimax lower bound of $Ω(d/Γ^2)$ for sample costs of reliable tests, dominating prior asymptotic lower bounds by capturing the dependence on $d$, and thus elucidating a basic insight missing in the extant literature on such problems.
title Testing the Feasibility of Linear Programs with Bandit Feedback
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2406.15648