REVIEW 5 cited by
Simulation-free Schr\"odinger bridges via score and flow matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
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 Schr\"odinger 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.
Forward citations
Cited by 5 Pith papers
-
Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior
Feynman-Kac particle steering, previously diffusion-only, is derived for conditional flow matching and used to generate chirality-correct chemical transition states.
-
Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching
MAC improves few-step flow-matching generation by up-weighting couplings with the lowest prediction error under the current model.
-
Materials Behavior as Mechanism Ensembles: A Probabilistic Framework for Emergent Behaviors
Materials phenomena such as fatigue crack growth are framed as conditional probability landscapes over competing unit mechanisms, to be inferred from multiscale simulation and multimodal data and then optimized toward...
-
Private Continuous-Time Synthetic Trajectory Generation via Mean-Field Langevin Dynamics
A differentially private particle-gradient algorithm generates continuous-time synthetic trajectories from one snapshot per person, but its headline recovery rate applies only to a non-private infinite-particle idealization.
-
Bidirectional Diffusion Bridge Models
BDBM uses a single masked noise-prediction network to model both forward and backward diffusion bridges between two image distributions, enabling bidirectional translation at roughly half the model cost.
Discussion (0). Continue with ORCID to comment.