AI RESEARCH
Total Variation Guarantees for Sampling with Stochastic Localization
arXiv CS.LG
•
ArXi:2603.29555v1 Announce Type: new Motivated by the success of score-based generative models, a number of diffusion-based algorithms have recently been proposed for the problem of sampling from a probability measure whose unnormalized density can be accessed. Among them, Grenioux