Generalization of Hamiltonian algorithms

Andreas Maurer

NeurIPS 2024poster1 citations

Generalization of Hamiltonian algorithms

Abstract

A method to prove generalization results for a class of stochastic learning algorithms is presented. It applies whenever the algorithm generates a distribution, which is absolutely continuous distribution relative to some a-priori measure, and the logarithm of its density is exponentially concentrated about its mean. Applications include bounds for the Gibbs algorithm and randomizations of stable deterministic algorithms, combinations thereof and PAC-Bayesian bounds with data-dependent priors.

Generalizationstochastic algorithmsconcentration inequalitiesPAC-Bayes

BibTeX

@inproceedings{
maurer2024generalization,
title={Generalization of Hamiltonian algorithms},
author={Andreas Maurer},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=0cSQ1Sg7db}
}