Generative Fractional Diffusion Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913568630243328 |
|---|---|
| author | Nobis, Gabriel Springenberg, Maximilian Aversa, Marco Detzel, Michael Daems, Rembert Murray-Smith, Roderick Nakajima, Shinichi Lapuschkin, Sebastian Ermon, Stefano Birdal, Tolga Opper, Manfred Knochenhauer, Christoph Oala, Luis Samek, Wojciech |
| author_facet | Nobis, Gabriel Springenberg, Maximilian Aversa, Marco Detzel, Michael Daems, Rembert Murray-Smith, Roderick Nakajima, Shinichi Lapuschkin, Sebastian Ermon, Stefano Birdal, Tolga Opper, Manfred Knochenhauer, Christoph Oala, Luis Samek, Wojciech |
| contents | We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Although diffusion models have excelled at capturing data distributions, they still suffer from various limitations such as slow convergence, mode-collapse on imbalanced data, and lack of diversity. These issues are partially linked to the use of light-tailed Brownian motion (BM) with independent increments. In this paper, we replace BM with an approximation of its non-Markovian counterpart, fractional Brownian motion (fBM), characterized by correlated increments and Hurst index $H \in (0,1)$, where $H=0.5$ recovers the classical BM. To ensure tractable inference and learning, we employ a recently popularized Markov approximation of fBM (MA-fBM) and derive its reverse-time model, resulting in generative fractional diffusion models (GFDM). We characterize the forward dynamics using a continuous reparameterization trick and propose augmented score matching to efficiently learn the score function, which is partly known in closed form, at minimal added cost. The ability to drive our diffusion model via MA-fBM offers flexibility and control. $H \leq 0.5$ enters the regime of rough paths whereas $H>0.5$ regularizes diffusion paths and invokes long-term memory. The Markov approximation allows added control by varying the number of Markov processes linearly combined to approximate fBM. Our evaluations on real image datasets demonstrate that GFDM achieves greater pixel-wise diversity and enhanced image quality, as indicated by a lower FID, offering a promising alternative to traditional diffusion models |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_17638 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Generative Fractional Diffusion Models Nobis, Gabriel Springenberg, Maximilian Aversa, Marco Detzel, Michael Daems, Rembert Murray-Smith, Roderick Nakajima, Shinichi Lapuschkin, Sebastian Ermon, Stefano Birdal, Tolga Opper, Manfred Knochenhauer, Christoph Oala, Luis Samek, Wojciech Machine Learning I.2.4; F.4.1; G.3 We introduce the first continuous-time score-based generative model that leverages fractional diffusion processes for its underlying dynamics. Although diffusion models have excelled at capturing data distributions, they still suffer from various limitations such as slow convergence, mode-collapse on imbalanced data, and lack of diversity. These issues are partially linked to the use of light-tailed Brownian motion (BM) with independent increments. In this paper, we replace BM with an approximation of its non-Markovian counterpart, fractional Brownian motion (fBM), characterized by correlated increments and Hurst index $H \in (0,1)$, where $H=0.5$ recovers the classical BM. To ensure tractable inference and learning, we employ a recently popularized Markov approximation of fBM (MA-fBM) and derive its reverse-time model, resulting in generative fractional diffusion models (GFDM). We characterize the forward dynamics using a continuous reparameterization trick and propose augmented score matching to efficiently learn the score function, which is partly known in closed form, at minimal added cost. The ability to drive our diffusion model via MA-fBM offers flexibility and control. $H \leq 0.5$ enters the regime of rough paths whereas $H>0.5$ regularizes diffusion paths and invokes long-term memory. The Markov approximation allows added control by varying the number of Markov processes linearly combined to approximate fBM. Our evaluations on real image datasets demonstrate that GFDM achieves greater pixel-wise diversity and enhanced image quality, as indicated by a lower FID, offering a promising alternative to traditional diffusion models |
| title | Generative Fractional Diffusion Models |
| topic | Machine Learning I.2.4; F.4.1; G.3 |
| url | https://arxiv.org/abs/2310.17638 |