2025/08/30 by Ezra Erives, Bowen Jing, Erives, Ezra +5
Computer Science · Materials Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning in Materials Science #Model Reduction and Neural Networks
paper · pdf · doi:10.48550/arxiv.2509.00316
openalex publication_date 2025/08/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source to target. A crucial design choice in the training phase of such samplers is the proposal distribution by which locations are generated at which to evaluate the loss. Previous work has obtained such a proposal distribution by combining a partially learned transport with annealed Langevin dynamics. However, isolated modes and other pathological properties of the annealing path imply that such proposals achieve insufficient exploration and thereby lower performance post training. To remedy this, we propose continuously tempered diffusion samplers, which leverage exploration techniques developed in the context of molecular dynamics to improve proposal distributions. Specifically, a family of distributions across different temperatures is introduced to lower energy barriers at higher temperatures and drive exploration at the lower temperature of interest. We empirically validate improved sampler performance driven by extended exploration. Code is available at https://github.com/eje24/ctds.