Discrete vs. Continuous Trade-offs for Generative Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913627455356928 |
|---|---|
| author | Korrapati, Jathin Baranwal, Tanish Shah, Rahul |
| author_facet | Korrapati, Jathin Baranwal, Tanish Shah, Rahul |
| contents | This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic processes and Brownian motion to model complex data distributions. These models employ forward and reverse diffusion processes defined through stochastic differential equations (SDEs) to iteratively add and remove noise, enabling high-quality data generation. By analyzing the performance bounds of these models, we demonstrate how score estimation errors propagate through the reverse process and bound the total variation distance using discrete Girsanov transformations, Pinsker's inequality, and the data processing inequality (DPI) for an information theoretic lens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discrete vs. Continuous Trade-offs for Generative Models Korrapati, Jathin Baranwal, Tanish Shah, Rahul Machine Learning Artificial Intelligence Information Theory Numerical Analysis Primary 68T07, Secondary 60H10, 94A15, 68Q87 This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic processes and Brownian motion to model complex data distributions. These models employ forward and reverse diffusion processes defined through stochastic differential equations (SDEs) to iteratively add and remove noise, enabling high-quality data generation. By analyzing the performance bounds of these models, we demonstrate how score estimation errors propagate through the reverse process and bound the total variation distance using discrete Girsanov transformations, Pinsker's inequality, and the data processing inequality (DPI) for an information theoretic lens. |
| title | Discrete vs. Continuous Trade-offs for Generative Models |
| topic | Machine Learning Artificial Intelligence Information Theory Numerical Analysis Primary 68T07, Secondary 60H10, 94A15, 68Q87 |
| url | https://arxiv.org/abs/2412.19114 |