Évènement

Julien Audiffren
University of Fribourg
https://scholar.google.fr/citations?user=7jcEx7cAAAAJ&hl=fr

Date(s) : 26/03/2021   iCal
14h30 - 15h30

In this presentation we discuss a variant of the continuous multi-armed bandits problem, called the threshold estimation problem, which is at the heart of many psychometric experiment. Here, the objective is to estimate the sensitivity threshold for an unknown psychometric function Ψ, 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 Ψ 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.

https://hal.archives-ouvertes.fr/hal-02448282v1

Catégories

• Séminaire