Back to Search Start Over

Misclassification excess risk bounds for PAC-Bayesian classification via convexified loss

Authors :
Mai, The Tien
Publication Year :
2024

Abstract

PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen loss function. In classification tasks, due to the non-convex nature of the 0-1 loss, a convex surrogate loss is often used, and thus current PAC-Bayesian bounds are primarily specified for this convex surrogate. This work shifts its focus to providing misclassification excess risk bounds for PAC-Bayesian classification when using a convex surrogate loss. Our key ingredient here is to leverage PAC-Bayesian relative bounds in expectation rather than relying on PAC-Bayesian bounds in probability. We demonstrate our approach in several important applications.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2408.08675
Document Type :
Working Paper