Saved in:
Bibliographic Details
Main Authors: Kim, Sanghwa, Ahn, Dohyun, Min, Seungki
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.07862
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916998336741376
author Kim, Sanghwa
Ahn, Dohyun
Min, Seungki
author_facet Kim, Sanghwa
Ahn, Dohyun
Min, Seungki
contents We study the problem of estimating a continuous ability parameter from sequential binary responses by actively asking questions with varying difficulties, a setting that arises naturally in adaptive testing and online preference learning. Our goal is to certify that the estimate lies within a desired margin of error, using as few queries as possible. We propose a simple algorithm that adaptively selects questions to maximize Fisher information and updates the estimate using a method-of-moments approach, paired with a novel test statistic to decide when the estimate is accurate enough. We prove that this Fisher-tracking strategy achieves optimal performance in both fixed-confidence and fixed-budget regimes, which are commonly invested in the best-arm identification literature. Our analysis overcomes a key technical challenge in the fixed-budget setting -- handling the dependence between the evolving estimate and the query distribution -- by exploiting a structural symmetry in the model and combining large deviation tools with Ville's inequality. Our results provide rigorous theoretical support for simple and efficient adaptive testing procedures.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07862
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses
Kim, Sanghwa
Ahn, Dohyun
Min, Seungki
Machine Learning
We study the problem of estimating a continuous ability parameter from sequential binary responses by actively asking questions with varying difficulties, a setting that arises naturally in adaptive testing and online preference learning. Our goal is to certify that the estimate lies within a desired margin of error, using as few queries as possible. We propose a simple algorithm that adaptively selects questions to maximize Fisher information and updates the estimate using a method-of-moments approach, paired with a novel test statistic to decide when the estimate is accurate enough. We prove that this Fisher-tracking strategy achieves optimal performance in both fixed-confidence and fixed-budget regimes, which are commonly invested in the best-arm identification literature. Our analysis overcomes a key technical challenge in the fixed-budget setting -- handling the dependence between the evolving estimate and the query distribution -- by exploiting a structural symmetry in the model and combining large deviation tools with Ville's inequality. Our results provide rigorous theoretical support for simple and efficient adaptive testing procedures.
title On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses
topic Machine Learning
url https://arxiv.org/abs/2510.07862