Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2506.16471 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912692468449280 |
|---|---|
| author | Akhound-Sadegh, Tara Lee, Jungyoon Bose, Avishek Joey De Bortoli, Valentin Doucet, Arnaud Bronstein, Michael M. Beaini, Dominique Ravanbakhsh, Siamak Neklyudov, Kirill Tong, Alexander |
| author_facet | Akhound-Sadegh, Tara Lee, Jungyoon Bose, Avishek Joey De Bortoli, Valentin Doucet, Arnaud Bronstein, Michael M. Beaini, Dominique Ravanbakhsh, Siamak Neklyudov, Kirill Tong, Alexander |
| contents | Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising approach towards this challenge is the design of amortized samplers that borrow key ideas, such as probability path design, from state-of-the-art generative diffusion models. However, all existing diffusion-based samplers remain unable to draw samples from distributions at the scale of even simple molecular systems. In this paper, we propose Progressive Inference-Time Annealing (PITA), a novel framework to learn diffusion-based samplers that combines two complementary interpolation techniques: I.) Annealing of the Boltzmann distribution and II.) Diffusion smoothing. PITA trains a sequence of diffusion models from high to low temperatures by sequentially training each model at progressively higher temperatures, leveraging engineered easy access to samples of the temperature-annealed target density. In the subsequent step, PITA enables simulating the trained diffusion model to procure training samples at a lower temperature for the next diffusion model through inference-time annealing using a novel Feynman-Kac PDE combined with Sequential Monte Carlo. Empirically, PITA enables, for the first time, equilibrium sampling of N-body particle systems, Alanine Dipeptide, and tripeptides in Cartesian coordinates with dramatically lower energy function evaluations. Code available at: https://github.com/taraak/pita |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities Akhound-Sadegh, Tara Lee, Jungyoon Bose, Avishek Joey De Bortoli, Valentin Doucet, Arnaud Bronstein, Michael M. Beaini, Dominique Ravanbakhsh, Siamak Neklyudov, Kirill Tong, Alexander Machine Learning Artificial Intelligence Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising approach towards this challenge is the design of amortized samplers that borrow key ideas, such as probability path design, from state-of-the-art generative diffusion models. However, all existing diffusion-based samplers remain unable to draw samples from distributions at the scale of even simple molecular systems. In this paper, we propose Progressive Inference-Time Annealing (PITA), a novel framework to learn diffusion-based samplers that combines two complementary interpolation techniques: I.) Annealing of the Boltzmann distribution and II.) Diffusion smoothing. PITA trains a sequence of diffusion models from high to low temperatures by sequentially training each model at progressively higher temperatures, leveraging engineered easy access to samples of the temperature-annealed target density. In the subsequent step, PITA enables simulating the trained diffusion model to procure training samples at a lower temperature for the next diffusion model through inference-time annealing using a novel Feynman-Kac PDE combined with Sequential Monte Carlo. Empirically, PITA enables, for the first time, equilibrium sampling of N-body particle systems, Alanine Dipeptide, and tripeptides in Cartesian coordinates with dramatically lower energy function evaluations. Code available at: https://github.com/taraak/pita |
| title | Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2506.16471 |