Constrained Generative Modeling with Manually Bridged Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Naderiparizi, Saeid, Liang, Xiaoxuan, Zwartsenberg, Berend, Wood, Frank
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916633884229632
author Naderiparizi, Saeid
Liang, Xiaoxuan
Zwartsenberg, Berend
Wood, Frank
author_facet Naderiparizi, Saeid
Liang, Xiaoxuan
Zwartsenberg, Berend
Wood, Frank
contents In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form so-called diffusion bridges. We develop a mechanism for combining multiple such constraints so that the resulting multiply-constrained model remains a manual bridge that respects all constraints. We also develop a mechanism for training a diffusion model that respects such multiple constraints while also adapting it to match a data distribution. We develop and extend theory demonstrating the mathematical validity of our mechanisms. Additionally, we demonstrate our mechanism in constrained generative modeling tasks, highlighting a particular high-value application in modeling trajectory initializations for path planning and control in autonomous vehicles.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Constrained Generative Modeling with Manually Bridged Diffusion Models
Naderiparizi, Saeid
Liang, Xiaoxuan
Zwartsenberg, Berend
Wood, Frank
Machine Learning
In this paper we describe a novel framework for diffusion-based generative modeling on constrained spaces. In particular, we introduce manual bridges, a framework that expands the kinds of constraints that can be practically used to form so-called diffusion bridges. We develop a mechanism for combining multiple such constraints so that the resulting multiply-constrained model remains a manual bridge that respects all constraints. We also develop a mechanism for training a diffusion model that respects such multiple constraints while also adapting it to match a data distribution. We develop and extend theory demonstrating the mathematical validity of our mechanisms. Additionally, we demonstrate our mechanism in constrained generative modeling tasks, highlighting a particular high-value application in modeling trajectory initializations for path planning and control in autonomous vehicles.
title Constrained Generative Modeling with Manually Bridged Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2502.20371