Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.04495 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915420770926592 |
|---|---|
| author | Ikeda, Kotaro Uda, Tomoya Okanohara, Daisuke Ito, Sosuke |
| author_facet | Ikeda, Kotaro Uda, Tomoya Okanohara, Daisuke Ito, Sosuke |
| contents | We discuss a connection between a generative model, called the diffusion model, and nonequilibrium thermodynamics for the Fokker-Planck equation, called stochastic thermodynamics. Using techniques from stochastic thermodynamics, we derive the speed-accuracy relations for diffusion models, which are inequalities that relate the accuracy of data generation to the entropy production rate. This relation can be interpreted as the speed of the diffusion dynamics in the absence of the non-conservative force. From a stochastic thermodynamic perspective, our results provide quantitative insight into how best to generate data in diffusion models. The optimal learning protocol is introduced by the geodesic of space of the 2-Wasserstein distance in optimal transport theory. We numerically illustrate the validity of the speed-accuracy relations for diffusion models with different noise schedules and different data. We numerically discuss our results for optimal and suboptimal learning protocols. We also demonstrate the applicability of our results to data generation from the real-world image datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04495 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport Ikeda, Kotaro Uda, Tomoya Okanohara, Daisuke Ito, Sosuke Statistical Mechanics Machine Learning We discuss a connection between a generative model, called the diffusion model, and nonequilibrium thermodynamics for the Fokker-Planck equation, called stochastic thermodynamics. Using techniques from stochastic thermodynamics, we derive the speed-accuracy relations for diffusion models, which are inequalities that relate the accuracy of data generation to the entropy production rate. This relation can be interpreted as the speed of the diffusion dynamics in the absence of the non-conservative force. From a stochastic thermodynamic perspective, our results provide quantitative insight into how best to generate data in diffusion models. The optimal learning protocol is introduced by the geodesic of space of the 2-Wasserstein distance in optimal transport theory. We numerically illustrate the validity of the speed-accuracy relations for diffusion models with different noise schedules and different data. We numerically discuss our results for optimal and suboptimal learning protocols. We also demonstrate the applicability of our results to data generation from the real-world image datasets. |
| title | Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport |
| topic | Statistical Mechanics Machine Learning |
| url | https://arxiv.org/abs/2407.04495 |