MMODELYST
Papers/Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
PAP

Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation

May 8, 2026

arXiv
Abstract

We study Slowly Annealed Langevin Dynamics (SALD), a sampler for tracking a path of moving target distributions and approximating the terminal target through time slowdown. We establish non-asymptotic convergence guarantees via a KL differential inequality, showing that slowdown improves tracking through contraction of intermediate targets and the complexity of the path. Motivated by training-free guided generation with pretrained score-based generative models, we further introduce Velocity-Aware SALD (VA-SALD), which explicitly incorporates the underlying marginal distributions of the pretrained model and uses slowdown to correct the additional deviation induced by guidance. This yields a principled framework for training-free guided generation for diffusion-based and related generative model families, together with convergence guarantees that clarify the roles of intermediate functional inequalities and guidance bias. Code is available at https://github.com/anitan0925/sald.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Atsushi Nitanda, Dake Bu, Yueming Lyu, Tanya Veeravalli
Your notes (browser-local)
saved
arXiv:2605.07950