Pith. sign in

REVIEW 2 cited by

Stochastic Optimal Control 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

arxiv 2312.02027 v5 pith:OHSRBAQ4 submitted 2023-12-04 math.OC cs.LGcs.NAmath.NAmath.PRstat.ML

classification math.OCcs.LGcs.NAmath.NAmath.PRstat.ML
keywords controlmatchingoptimalstochasticfieldlossreparameterizationvector
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Stochastic optimal control, which has the goal of driving the behavior of noisy systems, is broadly applicable in science, engineering and artificial intelligence. Our work introduces Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control that stems from the same philosophy as the conditional score matching loss for diffusion models. That is, the control is learned via a least squares problem by trying to fit a matching vector field. The training loss, which is closely connected to the cross-entropy loss, is optimized with respect to both the control function and a family of reparameterization matrices which appear in the matching vector field. The optimization with respect to the reparameterization matrices aims at minimizing the variance of the matching vector field. Experimentally, our algorithm achieves lower error than all the existing IDO techniques for stochastic optimal control for three out of four control problems, in some cases by an order of magnitude. The key idea underlying SOCM is the path-wise reparameterization trick, a novel technique that may be of independent interest. Code at https://github.com/facebookresearch/SOC-matching

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Optimal Scheduling of Dynamic Transport

    stat.ML 2025-04 conditional novelty 8.0 of 10

    For a fixed transport map with symmetric positive definite Jacobian, the closed-form optimal schedule minimizing the uniform spatial Lipschitz constant of the flow velocity is an exponential two-phase curve that achie...

  2. FlowBack-Adjoint: Physics-Aware and Energy-Guided Conditional Flow-Matching for All-Atom Protein Backmapping

    physics.chem-ph 2025-08 conditional novelty 6.0 of 10

    FlowBack-Adjoint fine-tunes a flow-matching backmapping model with molecular mechanics energy gradients, reducing clashes and bond errors and producing lower-energy all-atom protein reconstructions.

Pith tools