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
Signed reviews
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
Forward citations
Cited by 2 Pith papers
-
Optimal Scheduling of Dynamic Transport
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...
-
FlowBack-Adjoint: Physics-Aware and Energy-Guided Conditional Flow-Matching for All-Atom Protein Backmapping
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.
Discussion (0). Continue with ORCID to comment.