Saved in:
Bibliographic Details
Main Author: Maurer, Andreas
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.14469
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929478435864576
author Maurer, Andreas
author_facet Maurer, Andreas
contents The paper proves generalization results for a class of stochastic learning algorithms. The method applies whenever the algorithm generates an absolutely continuous distribution relative to some a-priori measure and the Radon Nikodym derivative has subgaussian concentration. Applications are bounds for the Gibbs algorithm and randomizations of stable deterministic algorithms as well as PAC-Bayesian bounds with data-dependent priors.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14469
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalization of Hamiltonian algorithms
Maurer, Andreas
Machine Learning
The paper proves generalization results for a class of stochastic learning algorithms. The method applies whenever the algorithm generates an absolutely continuous distribution relative to some a-priori measure and the Radon Nikodym derivative has subgaussian concentration. Applications are bounds for the Gibbs algorithm and randomizations of stable deterministic algorithms as well as PAC-Bayesian bounds with data-dependent priors.
title Generalization of Hamiltonian algorithms
topic Machine Learning
url https://arxiv.org/abs/2405.14469