Saved in:
Bibliographic Details
Main Author: Tang, Sophia
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18992
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915875520512000
author Tang, Sophia
author_facet Tang, Sophia
contents At the core of modern generative modeling frameworks, including diffusion models, score-based models, and flow matching, is the task of transforming a simple prior distribution into a complex target distribution through stochastic paths in probability space. Schrödinger bridges provide a unifying principle underlying these approaches, framing the problem as determining an optimal stochastic bridge between marginal distribution constraints with minimal-entropy deviations from a pre-defined reference process. This guide develops the mathematical foundations of the Schrödinger bridge problem, drawing on optimal transport, stochastic control, and path-space optimization, and focuses on its dynamic formulation with direct connections to modern generative modeling. We build a comprehensive toolkit for constructing Schrödinger bridges from first principles, and show how these constructions give rise to generalized and task-specific computational methods.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18992
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Foundations of Schrödinger Bridges for Generative Modeling
Tang, Sophia
Machine Learning
Artificial Intelligence
At the core of modern generative modeling frameworks, including diffusion models, score-based models, and flow matching, is the task of transforming a simple prior distribution into a complex target distribution through stochastic paths in probability space. Schrödinger bridges provide a unifying principle underlying these approaches, framing the problem as determining an optimal stochastic bridge between marginal distribution constraints with minimal-entropy deviations from a pre-defined reference process. This guide develops the mathematical foundations of the Schrödinger bridge problem, drawing on optimal transport, stochastic control, and path-space optimization, and focuses on its dynamic formulation with direct connections to modern generative modeling. We build a comprehensive toolkit for constructing Schrödinger bridges from first principles, and show how these constructions give rise to generalized and task-specific computational methods.
title Foundations of Schrödinger Bridges for Generative Modeling
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.18992