Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917878662430720 |
|---|---|
| author | Kaba, Kentaro Shimizu, Reo Ohzeki, Masayuki Sughiyama, Yuki |
| author_facet | Kaba, Kentaro Shimizu, Reo Ohzeki, Masayuki Sughiyama, Yuki |
| contents | Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g., score-based models) only learn the backward process, more flexible frameworks have been proposed to also learn the forward process by employing the Schrödinger bridge (SB). However, due to the complexity of the mathematical structure behind SB-type models, we can not easily give an intuitive understanding of their objective function. In this work, we propose a unified framework to construct diffusion models by reinterpreting the SB-type models as an extension of variational autoencoders. In this context, the data processing inequality plays a crucial role. As a result, we find that the objective function consists of the prior loss and drift matching parts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18237 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders Kaba, Kentaro Shimizu, Reo Ohzeki, Masayuki Sughiyama, Yuki Machine Learning Generative diffusion models use time-forward and backward stochastic differential equations to connect the data and prior distributions. While conventional diffusion models (e.g., score-based models) only learn the backward process, more flexible frameworks have been proposed to also learn the forward process by employing the Schrödinger bridge (SB). However, due to the complexity of the mathematical structure behind SB-type models, we can not easily give an intuitive understanding of their objective function. In this work, we propose a unified framework to construct diffusion models by reinterpreting the SB-type models as an extension of variational autoencoders. In this context, the data processing inequality plays a crucial role. As a result, we find that the objective function consists of the prior loss and drift matching parts. |
| title | Schödinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.18237 |