AI RESEARCH
Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation
arXiv CS.LG
•
ArXi:2605.07950v1 Announce Type: new 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