paper-with-me

홈 › Papers

Critically Damped Third-Order Langevin Dynamics

2024-09-12 · Benjamin Sterling, Monica Bugallo

While systems analysis has been studied for decades in the context of control theory, it has only been recently used to improve the convergence of Denoising Diffusion Probabilistic Models. This work describes a novel improvement to Third- Order Langevin Dynamics (TOLD), a recent diffusion method that performs better than its predecessors. This improvement, abbreviated TOLD++, is carried out by critically damping the TOLD forward transition matrix similarly to Dockhorn's Critically-Damped Langevin Dynamics (CLD). Specifically, it exploits eigen-analysis of the forward transition matrix to derive the optimal set of dynamics under the original TOLD scheme. TOLD++ is theoretically guaranteed to converge faster than TOLD, and its faster convergence is verified on the Swiss Roll toy dataset and CIFAR-10 dataset according to the FID metric.

📄 PDF Abstract BibTeX arXiv:2409.07697

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
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

Underdamped Langevin MCMC with third order convergence

2025-08-22 · Maximilian Scott, Dáire O'Kane, Andraž Jelinčič, James Foster arxiv

In this paper, we propose a new numerical method for the underdamped Langevin diffusion (ULD) and present a non-asymptotic analysis of its sampling error in the 2-Wasserstein distance when the $d$-dimensional target dist…

Defending Diffusion Models Against Membership Inference Attacks via Higher-Order Langevin Dynamics

2025-09-17 · Benjamin Sterling, Yousef El-Laham, Mónica F. Bugallo arxiv

Recent advances in generative artificial intelligence applications have raised new data security concerns. This paper focuses on defending diffusion models against membership inference attacks. This type of attack occurs…

Sharp convergence rates for Langevin dynamics in the nonconvex setting

2018-05-04 · Xiang Cheng, Niladri S. Chatterji, Yasin Abbasi-Yadkori, Peter L. Bartlett 외

We study the problem of sampling from a distribution $p^*(x) \propto \exp\left(-U(x)\right)$, where the function $U$ is $L$-smooth everywhere and $m$-strongly convex outside a ball of radius $R$, but potentially nonconve…

Wasserstein Convergence of Critically Damped Langevin Diffusions

2025-11-04 · Stanislas Strasman, Sobihan Surendran, Claire Boyer, Sylvain Le Corff 외 arxiv

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical m…

Fisher information dissipation for time inhomogeneous stochastic differential equations

2024-02-01 · Qi Feng, Xinzhe Zuo, Wuchen Li

We provide a Lyapunov convergence analysis for time-inhomogeneous variable coefficient stochastic differential equations (SDEs). Three typical examples include overdamped, irreversible drift, and underdamped Langevin dyn…