LightSBB-M: Bridging Schrödinger and Bass for Generative Diffusion Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918483859603456 |
|---|---|
| author | Alouadi, Alexandre Henry-Labordère, Pierre Loeper, Grégoire Mazhar, Othmane Pham, Huyên Touzi, Nizar |
| author_facet | Alouadi, Alexandre Henry-Labordère, Pierre Loeper, Grégoire Mazhar, Othmane Pham, Huyên Touzi, Nizar |
| contents | The Schrodinger Bridge and Bass (SBB) formulation, which jointly controls drift and volatility, is an established extension of the classical Schrodinger Bridge (SB). Building on this framework, we introduce LightSBB-M, an algorithm that computes the optimal SBB transport plan in only a few iterations. The method exploits a dual representation of the SBB objective to obtain analytic expressions for the optimal drift and volatility, and it incorporates a tunable parameter beta greater than zero that interpolates between pure drift (the Schrodinger Bridge) and pure volatility (Bass martingale transport). We show that LightSBB-M achieves the lowest 2-Wasserstein distance on synthetic datasets against state-of-the-art SB and diffusion baselines with up to 32 percent improvement. We also illustrate the generative capability of the framework on an unpaired image-to-image translation task (adult to child faces in FFHQ). These findings demonstrate that LightSBB-M provides a scalable, high-fidelity SBB solver that outperforms existing SB and diffusion baselines across both synthetic and real-world generative tasks. The code is available at https://github.com/alexouadi/LightSBB-M. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_19312 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LightSBB-M: Bridging Schrödinger and Bass for Generative Diffusion Modeling Alouadi, Alexandre Henry-Labordère, Pierre Loeper, Grégoire Mazhar, Othmane Pham, Huyên Touzi, Nizar Machine Learning Systems and Control Computation The Schrodinger Bridge and Bass (SBB) formulation, which jointly controls drift and volatility, is an established extension of the classical Schrodinger Bridge (SB). Building on this framework, we introduce LightSBB-M, an algorithm that computes the optimal SBB transport plan in only a few iterations. The method exploits a dual representation of the SBB objective to obtain analytic expressions for the optimal drift and volatility, and it incorporates a tunable parameter beta greater than zero that interpolates between pure drift (the Schrodinger Bridge) and pure volatility (Bass martingale transport). We show that LightSBB-M achieves the lowest 2-Wasserstein distance on synthetic datasets against state-of-the-art SB and diffusion baselines with up to 32 percent improvement. We also illustrate the generative capability of the framework on an unpaired image-to-image translation task (adult to child faces in FFHQ). These findings demonstrate that LightSBB-M provides a scalable, high-fidelity SBB solver that outperforms existing SB and diffusion baselines across both synthetic and real-world generative tasks. The code is available at https://github.com/alexouadi/LightSBB-M. |
| title | LightSBB-M: Bridging Schrödinger and Bass for Generative Diffusion Modeling |
| topic | Machine Learning Systems and Control Computation |
| url | https://arxiv.org/abs/2601.19312 |