Diffeomorphic Measure Matching with Kernels for Generative Modeling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Pandey, Biraj, Hosseini, Bamdad, Batlle, Pau, Owhadi, Houman
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911776160874496
author Pandey, Biraj
Hosseini, Bamdad
Batlle, Pau
Owhadi, Houman
author_facet Pandey, Biraj
Hosseini, Bamdad
Batlle, Pau
Owhadi, Houman
contents This article presents a general framework for the transport of probability measures towards minimum divergence generative modeling and sampling using ordinary differential equations (ODEs) and Reproducing Kernel Hilbert Spaces (RKHSs), inspired by ideas from diffeomorphic matching and image registration. A theoretical analysis of the proposed method is presented, giving a priori error bounds in terms of the complexity of the model, the number of samples in the training set, and model misspecification. An extensive suite of numerical experiments further highlights the properties, strengths, and weaknesses of the method and extends its applicability to other tasks, such as conditional simulation and inference.
format Preprint
id arxiv_https___arxiv_org_abs_2402_08077
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffeomorphic Measure Matching with Kernels for Generative Modeling
Pandey, Biraj
Hosseini, Bamdad
Batlle, Pau
Owhadi, Houman
Machine Learning
Dynamical Systems
Computation
35Q68 49Q22 62F15 68T07 62R07
This article presents a general framework for the transport of probability measures towards minimum divergence generative modeling and sampling using ordinary differential equations (ODEs) and Reproducing Kernel Hilbert Spaces (RKHSs), inspired by ideas from diffeomorphic matching and image registration. A theoretical analysis of the proposed method is presented, giving a priori error bounds in terms of the complexity of the model, the number of samples in the training set, and model misspecification. An extensive suite of numerical experiments further highlights the properties, strengths, and weaknesses of the method and extends its applicability to other tasks, such as conditional simulation and inference.
title Diffeomorphic Measure Matching with Kernels for Generative Modeling
topic Machine Learning
Dynamical Systems
Computation
35Q68 49Q22 62F15 68T07 62R07
url https://arxiv.org/abs/2402.08077