Value Gradient Sampler: Learning Invariant Value Functions for Equivariant Diffusion Sampling
Year: 2025
Type: preprint
Abstract: We propose the Value Gradient Sampler (VGS), a diffusion sampler parameterized by value functions. VGS generates samples from an unnormalized target density (i.e., energy) by evolving randomly initialized particles along the gradient of the value function. In many sampling problems where the target density exhibits invariant symmetries, value functions provide a novel approach to leveraging invariant networks for sampling by inducing an equivariant gradient flow, without requiring more complex equivariant networks. The value networks are trained via temporal difference learning, which supports off-policy training and other established reinforcement learning (RL) techniques. By combining advanced RL methods with efficient invariant networks, VGS achieves both the highest sample quality and the fastest sampling speed among our baselines on the 55-particle Lennard-Jones system.
Source: arXiv (Cornell University)
Authors: Hwang, Himchan, Jeong, Hyeokju, Shin, Dong Kyu, Park, Che-Sang, Kweon, Sehee, Yoon, Sangwoong, Park, Frank Chongwoo
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Funders: Microsoft Research, National Research Foundation, Ulsan National Institute of Science and Technology, Korea Institute for Advancement of Technology, National Research Foundation of Korea, Ministry of Science and ICT, South Korea, Microsoft Research Asia, Institute for Information and Communications Technology Promotion
OpenAlex ID: W4407764110