Progressive Tempering Sampler with Diffusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rissanen, Severi, OuYang, RuiKang, He, Jiajun, Chen, Wenlin, Heinonen, Markus, Solin, Arno, Hernández-Lobato, José Miguel
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917025526317056
author Rissanen, Severi
OuYang, RuiKang
He, Jiajun
Chen, Wenlin
Heinonen, Markus
Solin, Arno
Hernández-Lobato, José Miguel
author_facet Rissanen, Severi
OuYang, RuiKang
He, Jiajun
Chen, Wenlin
Heinonen, Markus
Solin, Arno
Hernández-Lobato, José Miguel
contents Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target evaluations. On the other hand, unlike a well-trained neural sampler, PT yields only dependent samples and needs to be rerun -- at considerable computational cost -- whenever new samples are required. To address these weaknesses, we propose the Progressive Tempering Sampler with Diffusion (PTSD), which trains diffusion models sequentially across temperatures, leveraging the advantages of PT to improve the training of neural samplers. We also introduce a novel method to combine high-temperature diffusion models to generate approximate lower-temperature samples, which are minimally refined using MCMC and used to train the next diffusion model. PTSD enables efficient reuse of sample information across temperature levels while generating well-mixed, uncorrelated samples. Our method significantly improves target evaluation efficiency, outperforming diffusion-based neural samplers.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05231
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Progressive Tempering Sampler with Diffusion
Rissanen, Severi
OuYang, RuiKang
He, Jiajun
Chen, Wenlin
Heinonen, Markus
Solin, Arno
Hernández-Lobato, José Miguel
Machine Learning
Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC approach, Parallel Tempering (PT), when it comes to the efficiency of target evaluations. On the other hand, unlike a well-trained neural sampler, PT yields only dependent samples and needs to be rerun -- at considerable computational cost -- whenever new samples are required. To address these weaknesses, we propose the Progressive Tempering Sampler with Diffusion (PTSD), which trains diffusion models sequentially across temperatures, leveraging the advantages of PT to improve the training of neural samplers. We also introduce a novel method to combine high-temperature diffusion models to generate approximate lower-temperature samples, which are minimally refined using MCMC and used to train the next diffusion model. PTSD enables efficient reuse of sample information across temperature levels while generating well-mixed, uncorrelated samples. Our method significantly improves target evaluation efficiency, outperforming diffusion-based neural samplers.
title Progressive Tempering Sampler with Diffusion
topic Machine Learning
url https://arxiv.org/abs/2506.05231