Simulation-free Schrödinger bridges via score and flow matching
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909133006962688 |
|---|---|
| author | Tong, Alexander Malkin, Nikolay Fatras, Kilian Atanackovic, Lazar Zhang, Yanlei Huguet, Guillaume Wolf, Guy Bengio, Yoshua |
| author_facet | Tong, Alexander Malkin, Nikolay Fatras, Kilian Atanackovic, Lazar Zhang, Yanlei Huguet, Guillaume Wolf, Guy Bengio, Yoshua |
| contents | We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions. Our method generalizes both the score-matching loss used in the training of diffusion models and the recently proposed flow matching loss used in the training of continuous normalizing flows. [SF]$^2$M interprets continuous-time stochastic generative modeling as a Schrödinger bridge problem. It relies on static entropy-regularized optimal transport, or a minibatch approximation, to efficiently learn the SB without simulating the learned stochastic process. We find that [SF]$^2$M is more efficient and gives more accurate solutions to the SB problem than simulation-based methods from prior work. Finally, we apply [SF]$^2$M to the problem of learning cell dynamics from snapshot data. Notably, [SF]$^2$M is the first method to accurately model cell dynamics in high dimensions and can recover known gene regulatory networks from simulated data. Our code is available in the TorchCFM package at https://github.com/atong01/conditional-flow-matching. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_03672 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Simulation-free Schrödinger bridges via score and flow matching Tong, Alexander Malkin, Nikolay Fatras, Kilian Atanackovic, Lazar Zhang, Yanlei Huguet, Guillaume Wolf, Guy Bengio, Yoshua Machine Learning We present simulation-free score and flow matching ([SF]$^2$M), a simulation-free objective for inferring stochastic dynamics given unpaired samples drawn from arbitrary source and target distributions. Our method generalizes both the score-matching loss used in the training of diffusion models and the recently proposed flow matching loss used in the training of continuous normalizing flows. [SF]$^2$M interprets continuous-time stochastic generative modeling as a Schrödinger bridge problem. It relies on static entropy-regularized optimal transport, or a minibatch approximation, to efficiently learn the SB without simulating the learned stochastic process. We find that [SF]$^2$M is more efficient and gives more accurate solutions to the SB problem than simulation-based methods from prior work. Finally, we apply [SF]$^2$M to the problem of learning cell dynamics from snapshot data. Notably, [SF]$^2$M is the first method to accurately model cell dynamics in high dimensions and can recover known gene regulatory networks from simulated data. Our code is available in the TorchCFM package at https://github.com/atong01/conditional-flow-matching. |
| title | Simulation-free Schrödinger bridges via score and flow matching |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2307.03672 |