Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis

Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis

We study the performance of Machine Learning (ML) classification techniques. Leveraging the theory of large deviations, we provide the mathematical conditions for a ML classifier to exhibit error probabilities that vanish exponentially, say <inline-formula><tex-math notation="LaTeX&quo...

Full description

Bibliographic Details
Main Authors: Paolo Braca, Leonardo M. Millefiori, Augusto Aubry, Stefano Marano, Antonio De Maio, Peter Willett
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Open Journal of Signal Processing
Subjects:
Machine learning
deep learning
large deviations principle
exact asymptotics
statistical hypothesis testing
Fenchel-Legendre transform
Online Access:https://ieeexplore.ieee.org/document/10008020/

Internet

https://ieeexplore.ieee.org/document/10008020/

Similar Items