REVIEW 2 cited by
Stochastic Normalizing Flows
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
read the original abstract
We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the underlying Brownian motion is treated as a latent variable and approximated, enabling efficient training of neural SDEs as random neural ordinary differential equations. These SDEs can be used for constructing efficient Markov chains to sample from the underlying distribution of a given dataset. Furthermore, by considering families of targeted SDEs with prescribed stationary distribution, we can apply VI to the optimization of hyperparameters in stochastic MCMC.
Forward citations
Cited by 2 Pith papers
-
Exactly solved Schr\"odinger equations with time-dependent Hamiltonians
Exact analytical series for evolution operators of four time-dependent 2-level Hamiltonians (including stochastic) are obtained via ★-algebra, path-sums and Omega calculus, yielding all-orders Floquet Hamiltonians.
-
SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations
SDE Matching trains latent SDEs by parameterizing posterior marginal distributions directly, so the variational objective is estimated with Monte Carlo samples instead of numerical SDE simulation.
Discussion (0). Continue with ORCID to comment.