Score-based Generative Modeling Through Backward Stochastic Differential
Equations: Inversion and Generation
- URL: http://arxiv.org/abs/2304.13224v1
- Date: Wed, 26 Apr 2023 01:15:35 GMT
- Title: Score-based Generative Modeling Through Backward Stochastic Differential
Equations: Inversion and Generation
- Authors: Zihao Wang
- Abstract summary: The proposed BSDE-based diffusion model represents a novel approach to diffusion modeling, which extends the application of differential equations (SDEs) in machine learning.
We demonstrate the theoretical guarantees of the model, the benefits of using Lipschitz networks for score matching, and its potential applications in various areas such as diffusion inversion, conditional diffusion, and uncertainty quantification.
- Score: 6.2255027793924285
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The proposed BSDE-based diffusion model represents a novel approach to
diffusion modeling, which extends the application of stochastic differential
equations (SDEs) in machine learning. Unlike traditional SDE-based diffusion
models, our model can determine the initial conditions necessary to reach a
desired terminal distribution by adapting an existing score function. We
demonstrate the theoretical guarantees of the model, the benefits of using
Lipschitz networks for score matching, and its potential applications in
various areas such as diffusion inversion, conditional diffusion, and
uncertainty quantification. Our work represents a contribution to the field of
score-based generative learning and offers a promising direction for solving
real-world problems.
Related papers
- On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution.
In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
arXiv Detail & Related papers (2024-05-18T15:59:41Z) - Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory [87.00653989457834]
Conditional diffusion models serve as the foundation of modern image synthesis and find extensive application in fields like computational biology and reinforcement learning.
Despite the empirical success, theory of conditional diffusion models is largely missing.
This paper bridges the gap by presenting a sharp statistical theory of distribution estimation using conditional diffusion models.
arXiv Detail & Related papers (2024-03-18T17:08:24Z) - Score-based Diffusion Models via Stochastic Differential Equations -- a Technical Tutorial [5.217870815854702]
This article focuses on the score-based diffusion models, with a particular focus on the formulation via differential equations (SDE)
After a gentle introduction, we discuss the two pillars in the diffusion modeling -- sampling and score matching.
Short proofs are given to illustrate the main idea of the stated results.
arXiv Detail & Related papers (2024-02-12T08:52:35Z) - Closing the ODE-SDE gap in score-based diffusion models through the
Fokker-Planck equation [0.562479170374811]
We rigorously describe the range of dynamics and approximations that arise when training score-based diffusion models.
We show numerically that conventional score-based diffusion models can exhibit significant differences between ODE- and SDE-induced distributions.
arXiv Detail & Related papers (2023-11-27T16:44:50Z) - 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) - Diffusion models for probabilistic programming [56.47577824219207]
Diffusion Model Variational Inference (DMVI) is a novel method for automated approximate inference in probabilistic programming languages (PPLs)
DMVI is easy to implement, allows hassle-free inference in PPLs without the drawbacks of, e.g., variational inference using normalizing flows, and does not make any constraints on the underlying neural network model.
arXiv Detail & Related papers (2023-11-01T12:17:05Z) - A Geometric Perspective on Diffusion Models [57.27857591493788]
We inspect the ODE-based sampling of a popular variance-exploding SDE.
We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
arXiv Detail & Related papers (2023-05-31T15:33:16Z) - Reflected Diffusion Models [93.26107023470979]
We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data.
Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
arXiv Detail & Related papers (2023-04-10T17:54:38Z) - An optimal control perspective on diffusion-based generative modeling [9.806130366152194]
We establish a connection between optimal control and generative models based on differential equations (SDEs)
In particular, we derive a Hamilton-Jacobi-Bellman equation that governs the evolution of the log-densities of the underlying SDE marginals.
We develop a novel diffusion-based method for sampling from unnormalized densities.
arXiv Detail & Related papers (2022-11-02T17:59:09Z) - A Flexible Diffusion Model [18.723160658185115]
We propose a framework for parameterizing the diffusion model, especially the spatial part of the forward SDE.
An abstract formalism is introduced with theoretical guarantees, and its connection with previous diffusion models is leveraged.
arXiv Detail & Related papers (2022-06-17T06:46:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.