Non-Asymptotic Analysis of (Sticky) Track-and-Stop

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Poiani, Riccardo, Bernasconi, Martino, Celli, Andrea
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912910835449856
author Poiani, Riccardo
Bernasconi, Martino
Celli, Andrea
author_facet Poiani, Riccardo
Bernasconi, Martino
Celli, Andrea
contents In pure exploration problems, a statistician sequentially collects information to answer a question about some stochastic and unknown environment. The probability of returning a wrong answer should not exceed a maximum risk parameter $δ$ and good algorithms make as few queries to the environment as possible. The Track-and-Stop algorithm is a pioneering method to solve these problems. Specifically, it is well-known that it enjoys asymptotic optimality sample complexity guarantees for $δ\to 0$ whenever the map from the environment to its correct answers is single-valued (e.g., best-arm identification with a unique optimal arm). The Sticky Track-and-Stop algorithm extends these results to settings where, for each environment, there might exist multiple correct answers (e.g., $ε$-optimal arm identification). Although both methods are optimal in the asymptotic regime, their non-asymptotic guarantees remain unknown. In this work, we fill this gap and provide non-asymptotic guarantees for both algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Non-Asymptotic Analysis of (Sticky) Track-and-Stop
Poiani, Riccardo
Bernasconi, Martino
Celli, Andrea
Machine Learning
In pure exploration problems, a statistician sequentially collects information to answer a question about some stochastic and unknown environment. The probability of returning a wrong answer should not exceed a maximum risk parameter $δ$ and good algorithms make as few queries to the environment as possible. The Track-and-Stop algorithm is a pioneering method to solve these problems. Specifically, it is well-known that it enjoys asymptotic optimality sample complexity guarantees for $δ\to 0$ whenever the map from the environment to its correct answers is single-valued (e.g., best-arm identification with a unique optimal arm). The Sticky Track-and-Stop algorithm extends these results to settings where, for each environment, there might exist multiple correct answers (e.g., $ε$-optimal arm identification). Although both methods are optimal in the asymptotic regime, their non-asymptotic guarantees remain unknown. In this work, we fill this gap and provide non-asymptotic guarantees for both algorithms.
title Non-Asymptotic Analysis of (Sticky) Track-and-Stop
topic Machine Learning
url https://arxiv.org/abs/2505.22475