Related papers: Adversarial Schrödinger Bridge Matching

Adversarial Schrödinger Bridge Matching

URL: http://arxiv.org/abs/2405.14449v1
Date: Thu, 23 May 2024 11:29:33 GMT
Title: Adversarial Schrödinger Bridge Matching
Authors: Nikita Gushchin, Daniil Selikhanovych, Sergei Kholkin, Evgeny Burnaev, Alexander Korotin,
Abstract summary: Iterative Markovian Fitting (IMF) procedure alternates between Markovian and reciprocal projections of continuous-time processes. We propose a novel Discrete-time IMF (D-IMF) procedure in which learning of processes is replaced by learning just a few transition probabilities in discrete time. 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.
Score: 66.39774923893103
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: The Schr\"odinger 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.

Related papers

Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting [60.003813643818965]
Iterative Markovian Fitting (IMF) procedure based on iterative reciprocal and Markovian projections has recently been proposed as a powerful method for solving the Schr"odinger Bridge problem. For the practical implementation of this procedure, it is crucial to alternate between fitting a forward and backward time diffusion at each iteration. In our work, we show that this closely connects with the pioneer approaches for the Schr"odinger Bridge based on the Iterative Proportional Fitting (IPF) procedure.
arXiv Detail & Related papers (2024-10-03T15:43:17Z)
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting [26.141054975797868]
We propose a novel Adaptive Multi-Scale Decomposition (AMD) framework for time series forecasting (TSF) Our framework decomposes time series into distinct temporal patterns at multiple scales, leveraging the Multi-Scale Decomposable Mixing (MDM) block. Our approach effectively models both temporal and channel dependencies and utilizes autocorrelation to refine multi-scale data integration.
arXiv Detail & Related papers (2024-06-06T05:27:33Z)
Neural Shrödinger Bridge Matching for Pansharpening [14.131205410479357]
Recent diffusion probabilistic models (DPM) in the field of pansharpening have been gradually gaining attention. We identify shortcomings in directly applying DPMs to the task of pansharpening as an inverse problem. We propose a Schr"odinger bridge matching method that addresses both issues.
arXiv Detail & Related papers (2024-04-17T14:17:05Z)
Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
We introduce a novel class of SDE-based solvers called GMS for diffusion models. Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
arXiv Detail & Related papers (2023-11-02T02:05:38Z)
Generative Fractional Diffusion Models [53.36835573822926]
We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Our evaluations on real image datasets demonstrate that GFDM achieves greater pixel-wise diversity and enhanced image quality, as indicated by a lower FID.
arXiv Detail & Related papers (2023-10-26T17:53:24Z)
Fast Diffusion Model [122.36693015093041]
Diffusion models (DMs) have been adopted across diverse fields with their abilities in capturing intricate data distributions. In this paper, we propose a Fast Diffusion Model (FDM) to significantly speed up DMs from a DM optimization perspective.
arXiv Detail & Related papers (2023-06-12T09:38:04Z)
Diffusion Schr\"odinger Bridge Matching [36.95088080680221]
We introduce Iterative Markovian Fitting (IMF) and Diffusion Schr"odinger Bridge Matching (DSBM) IMF is a new methodology for solving SB problems, and DSBM is a novel numerical algorithm for computing IMF iterates. We demonstrate the performance of DSBM on a variety of problems.
arXiv Detail & Related papers (2023-03-29T16:59:22Z)
Bayesian Pseudo-Coresets via Contrastive Divergence [5.479797073162603]
We introduce a novel approach for constructing pseudo-coresets by utilizing contrastive divergence. It eliminates the need for approximations in the pseudo-coreset construction process. We conduct extensive experiments on multiple datasets, demonstrating its superiority over existing BPC techniques.
arXiv Detail & Related papers (2023-03-20T17:13:50Z)
Pseudo Numerical Methods for Diffusion Models on Manifolds [77.40343577960712]
Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. DDPMs require hundreds to thousands of iterations to produce final samples. We propose pseudo numerical methods for diffusion models (PNDMs) PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup)
arXiv Detail & Related papers (2022-02-20T10:37:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.