Generalization of Hamiltonian algorithms
Machine Learning
2024-08-30 v2
Abstract
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.
Keywords
Cite
@article{arxiv.2405.14469,
title = {Generalization of Hamiltonian algorithms},
author = {Andreas Maurer},
journal= {arXiv preprint arXiv:2405.14469},
year = {2024}
}