AI RESEARCH
Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Models
arXiv CS.LG
•
ArXi:2211.01512v3 Announce Type: replace Motivated by the increasingly popular Score-based Generative Modeling (SGM), we study the Inexact Langevin Dynamics (ILD) and Inexact Langevin Algorithm (ILA) where a score function estimate is used in place of the exact score. We establish {\em stable} biased convergence guarantees in terms of the Kullback-Leibler (KL) divergence.