Enregistré dans:
Détails bibliographiques
Auteurs principaux: Blessing, Denis, Berner, Julius, Richter, Lorenz, Domingo-Enrich, Carles, Du, Yuanqi, Vahdat, Arash, Neumann, Gerhard
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.12511
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917339707998208
author Blessing, Denis
Berner, Julius
Richter, Lorenz
Domingo-Enrich, Carles
Du, Yuanqi
Vahdat, Arash
Neumann, Gerhard
author_facet Blessing, Denis
Berner, Julius
Richter, Lorenz
Domingo-Enrich, Carles
Du, Yuanqi
Vahdat, Arash
Neumann, Gerhard
contents Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practice, however, this optimization is challenging in particular if the target measure differs substantially from the prior. In this work, we therefore approach the problem by iteratively solving constrained problems incorporating trust regions that aim for approaching the target measure gradually in a systematic way. It turns out that this trust region based strategy can be understood as a geometric annealing from the prior to the target measure, where, however, the incorporated trust regions lead to a principled and educated way of choosing the time steps in the annealing path. We demonstrate in multiple optimal control applications that our novel method can improve performance significantly, including tasks in diffusion-based sampling, transition path sampling, and fine-tuning of diffusion models.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12511
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
Blessing, Denis
Berner, Julius
Richter, Lorenz
Domingo-Enrich, Carles
Du, Yuanqi
Vahdat, Arash
Neumann, Gerhard
Machine Learning
Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practice, however, this optimization is challenging in particular if the target measure differs substantially from the prior. In this work, we therefore approach the problem by iteratively solving constrained problems incorporating trust regions that aim for approaching the target measure gradually in a systematic way. It turns out that this trust region based strategy can be understood as a geometric annealing from the prior to the target measure, where, however, the incorporated trust regions lead to a principled and educated way of choosing the time steps in the annealing path. We demonstrate in multiple optimal control applications that our novel method can improve performance significantly, including tasks in diffusion-based sampling, transition path sampling, and fine-tuning of diffusion models.
title Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference
topic Machine Learning
url https://arxiv.org/abs/2508.12511