From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training

Julius Berner, Lorenz Richter, Marcin Sendera, Jarrid Rector-Brooks, Nikolay Malkin

Authors that are also TMLR Expert Reviewers: ~Julius_Berner1

Abstract: We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the generative and noising processes, using either differentiable simulation or off-policy reinforcement learning (RL). We prove equivalences between families of objectives in the limit of infinitesimal discretization steps, linking entropic RL methods (GFlowNets) with continuous-time objects (partial differential equations and path space measures). We further show that an appropriate choice of coarse time discretization during training allows greatly improved sample efficiency and the use of time-local objectives, achieving competitive performance on standard sampling benchmarks with reduced computational cost.

Certifications: Expert Certification

Submission Type: Regular submission (no more than 12 pages of main content)

Code: https://github.com/GFNOrg/gfn-diffusion/tree/stagger

Assigned Action Editor: ~Valentin_De_Bortoli1

Submission Number: 4992