2021-07-01-audiffren21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Dichotomous Optimistic Search to Quantify Human Perception	In this paper we address a variant of the continuous multi-armed bandits problem, called the threshold estimation problem, which is at the heart of many psychometric experiments. Here, the objective is to estimate the sensitivity threshold for an unknown psychometric function Psi, which is assumed to be non decreasing and continuous. Our algorithm, Dichotomous Optimistic Search (DOS), efficiently solves this task by taking inspiration from hierarchical multi-armed bandits and Black-box optimization. Compared to previous approaches, DOS is model free and only makes minimal assumption on Psi smoothness, while having strong theoretical guarantees that compares favorably to recent methods from both Psychophysics and Global Optimization. We also empirically evaluate DOS and show that it significantly outperforms these methods, both in experiments that mimics the conduct of a psychometric experiment, and in tests with large pulls budgets that illustrate the faster convergence rate.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	audiffren21a	0	Dichotomous Optimistic Search to Quantify Human Perception	414	424	414-424	414	false	Audiffren, Julien	given family Julien Audiffren	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/audiffren21a/audiffren21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/audiffren21a/audiffren21a-supp.pdf