Enregistré dans:
Détails bibliographiques
Auteurs principaux: Na, Kunwoo, Lee, Junghyun, Yun, Se-Young, Lim, Sungbin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.10219
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910873846546432
author Na, Kunwoo
Lee, Junghyun
Yun, Se-Young
Lim, Sungbin
author_facet Na, Kunwoo
Lee, Junghyun
Yun, Se-Young
Lim, Sungbin
contents Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.
format Preprint
id arxiv_https___arxiv_org_abs_2503_10219
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Probability-Flow ODE in Infinite-Dimensional Function Spaces
Na, Kunwoo
Lee, Junghyun
Yun, Se-Young
Lim, Sungbin
Machine Learning
Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation tasks where the underlying structure is inherently infinite-dimensional. To accelerate inference in such models, we derive, for the first time, an analog of the probability-flow ODE (PF-ODE) in infinite-dimensional function spaces. Leveraging this newly formulated PF-ODE, we reduce the number of function evaluations while maintaining sample quality in function generation tasks, including applications to PDEs.
title Probability-Flow ODE in Infinite-Dimensional Function Spaces
topic Machine Learning
url https://arxiv.org/abs/2503.10219