paper-with-me

홈 › Papers

Convergence of flow-based generative models via proximal gradient descent in Wasserstein space

2023-10-26 · Xiuyuan Cheng, Jianfeng Lu, Yixin Tan, Yao Xie

Flow-based generative models enjoy certain advantages in computing the data generation and the likelihood, and have recently shown competitive empirical performance. Compared to the accumulating theoretical studies on related score-based diffusion models, analysis of flow-based models, which are deterministic in both forward (data-to-noise) and reverse (noise-to-data) directions, remain sparse. In this paper, we provide a theoretical guarantee of generating data distribution by a progressive flow model, the so-called JKO flow model, which implements the Jordan-Kinderleherer-Otto (JKO) scheme in a normalizing flow network. Leveraging the exponential convergence of the proximal gradient descent (GD) in Wasserstein space, we prove the Kullback-Leibler (KL) guarantee of data generation by a JKO flow model to be $O(\varepsilon^2)$ when using $N \lesssim \log (1/\varepsilon)$ many JKO steps ($N$ Residual Blocks in the flow) where $\varepsilon $ is the error in the per-step first-order condition. The assumption on data density is merely a finite second moment, and the theory extends to data distributions without density and when there are inversion errors in the reverse process where we obtain KL-$W_2$ mixed error guarantees. The non-asymptotic convergence rate of the JKO-type $W_2$-proximal GD is proved for a general class of convex objective functionals that includes the KL divergence as a special case, which can be of independent interest. The analysis framework can extend to other first-order Wasserstein optimization schemes applied to flow-based generative models.

📄 PDF Abstract BibTeX arXiv:2310.17582

Code (1)

yixintan-zeta/jko_wass_grad 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity

2025-01-25 · Shuailong Zhu, Xiaohui Chen

The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algori…

Decoupled Asynchronous Proximal Stochastic Gradient Descent with Variance Reduction

2016-09-22 · Zhouyuan Huo, Bin Gu, Heng Huang

In the era of big data, optimizing large scale machine learning problems becomes a challenging task and draws significant attention. Asynchronous optimization algorithms come out as a promising solution. Recently, decoup…

A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates

2017-04-25 · Zhi Li, Wei Shi, Ming Yan

This paper proposes a novel proximal-gradient algorithm for a decentralized optimization problem with a composite objective containing smooth and non-smooth terms. Specifically, the smooth and nonsmooth terms are dealt w…

Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization

2022-01-31 · Samuel Hurault, Arthur Leclaire, Nicolas Papadakis

Plug-and-Play (PnP) methods solve ill-posed inverse problems through iterative proximal algorithms by replacing a proximal operator by a denoising operation. When applied with deep neural network denoisers, these methods…

DeblurringDenoisingImage RestorationSuper-Resolution

A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatch

2026-01-14 · Guixian Xu, Jinglai Li, Junqi Tang arxiv

In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the denoiser is trained on a different data distribution to the inference task at hand. T…