Adversarial Schrödinger Bridge Matching

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gushchin, Nikita, Selikhanovych, Daniil, Kholkin, Sergei, Burnaev, Evgeny, Korotin, Alexander
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910684370960384
author Gushchin, Nikita
Selikhanovych, Daniil
Kholkin, Sergei
Burnaev, Evgeny
Korotin, Alexander
author_facet Gushchin, Nikita
Selikhanovych, Daniil
Kholkin, Sergei
Burnaev, Evgeny
Korotin, Alexander
contents The Schrödinger Bridge (SB) problem offers a powerful framework for combining optimal transport and diffusion models. A promising recent approach to solve the SB problem is the Iterative Markovian Fitting (IMF) procedure, which alternates between Markovian and reciprocal projections of continuous-time stochastic processes. However, the model built by the IMF procedure has a long inference time due to using many steps of numerical solvers for stochastic differential equations. To address this limitation, we propose a novel Discrete-time IMF (D-IMF) procedure in which learning of stochastic processes is replaced by learning just a few transition probabilities in discrete time. Its great advantage is that in practice it can be naturally implemented using the Denoising Diffusion GAN (DD-GAN), an already well-established adversarial generative modeling technique. We show that our D-IMF procedure can provide the same quality of unpaired domain translation as the IMF, using only several generation steps instead of hundreds. We provide the code at https://github.com/Daniil-Selikhanovych/ASBM.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14449
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adversarial Schrödinger Bridge Matching
Gushchin, Nikita
Selikhanovych, Daniil
Kholkin, Sergei
Burnaev, Evgeny
Korotin, Alexander
Machine Learning
The Schrödinger Bridge (SB) problem offers a powerful framework for combining optimal transport and diffusion models. A promising recent approach to solve the SB problem is the Iterative Markovian Fitting (IMF) procedure, which alternates between Markovian and reciprocal projections of continuous-time stochastic processes. However, the model built by the IMF procedure has a long inference time due to using many steps of numerical solvers for stochastic differential equations. To address this limitation, we propose a novel Discrete-time IMF (D-IMF) procedure in which learning of stochastic processes is replaced by learning just a few transition probabilities in discrete time. Its great advantage is that in practice it can be naturally implemented using the Denoising Diffusion GAN (DD-GAN), an already well-established adversarial generative modeling technique. We show that our D-IMF procedure can provide the same quality of unpaired domain translation as the IMF, using only several generation steps instead of hundreds. We provide the code at https://github.com/Daniil-Selikhanovych/ASBM.
title Adversarial Schrödinger Bridge Matching
topic Machine Learning
url https://arxiv.org/abs/2405.14449