Saved in:
Bibliographic Details
Main Authors: Pasquale, Andrea, Krefl, Daniel, Carrazza, Stefano, Nielsen, Frank
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2303.05910
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929207258382336
author Pasquale, Andrea
Krefl, Daniel
Carrazza, Stefano
Nielsen, Frank
author_facet Pasquale, Andrea
Krefl, Daniel
Carrazza, Stefano
Nielsen, Frank
contents The estimation of probability density functions is a non trivial task that over the last years has been tackled with machine learning techniques. Successful applications can be obtained using models inspired by the Boltzmann machine (BM) architecture. In this manuscript, the product Jacobi-Theta Boltzmann machine (pJTBM) is introduced as a restricted version of the Riemann-Theta Boltzmann machine (RTBM) with diagonal hidden sector connection matrix. We show that score matching, based on the Fisher divergence, can be used to fit probability densities with the pJTBM more efficiently than with the original RTBM.
format Preprint
id arxiv_https___arxiv_org_abs_2303_05910
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Product Jacobi-Theta Boltzmann machines with score matching
Pasquale, Andrea
Krefl, Daniel
Carrazza, Stefano
Nielsen, Frank
Machine Learning
The estimation of probability density functions is a non trivial task that over the last years has been tackled with machine learning techniques. Successful applications can be obtained using models inspired by the Boltzmann machine (BM) architecture. In this manuscript, the product Jacobi-Theta Boltzmann machine (pJTBM) is introduced as a restricted version of the Riemann-Theta Boltzmann machine (RTBM) with diagonal hidden sector connection matrix. We show that score matching, based on the Fisher divergence, can be used to fit probability densities with the pJTBM more efficiently than with the original RTBM.
title Product Jacobi-Theta Boltzmann machines with score matching
topic Machine Learning
url https://arxiv.org/abs/2303.05910