Work

Approximate Hypothesis Testing

Year: 2025

Type: conference-paper

Abstract: We establish the sample complexity of Approximate Hypothesis Testing (AHT): Unlike in classical hypothesis testing, here we are only required to approximate the sample-generating distribution rather than determine it exactly.On finite hypothesis classes, we establish that the AHT sample complexity scales inversely with the multivariate Bhattacharyya distance (3) evaluated on a set of distributions considered to be the "most confusable" w.r.t. the desired approximation accuracy.

Source: IEEE Information Theory Workshop (ITW)

DOI: 10.1109/itw62417.2025.11240528

Authors: Nicolas Le Gouic, Robert Graczyk, Stefan Moser

Institutions: Institut Polytechnique de Paris, Laboratoire Traitement et Communication de l’Information, RhySearch (Switzerland), ETH Zurich, Signal and Information Processing Laboratory

Language: English

Topic: Machine Learning and Algorithms

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: European Research Council

OpenAlex ID: W4407118954

FWCI:

Cites:

Cited by:

Related to: 10