REVIEW 5 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
Stochastic Normalizing Flows
read the original abstract
The sampling of probability distributions specified up to a normalization constant is an important problem in both machine learning and statistical mechanics. While classical stochastic sampling methods such as Markov Chain Monte Carlo (MCMC) or Langevin Dynamics (LD) can suffer from slow mixing times there is a growing interest in using normalizing flows in order to learn the transformation of a simple prior distribution to the given target distribution. Here we propose a generalized and combined approach to sample target densities: Stochastic Normalizing Flows (SNF) -- an arbitrary sequence of deterministic invertible functions and stochastic sampling blocks. We show that stochasticity overcomes expressivity limitations of normalizing flows resulting from the invertibility constraint, whereas trainable transformations between sampling steps improve efficiency of pure MCMC/LD along the flow. By invoking ideas from non-equilibrium statistical mechanics we derive an efficient training procedure by which both the sampler's and the flow's parameters can be optimized end-to-end, and by which we can compute exact importance weights without having to marginalize out the randomness of the stochastic blocks. We illustrate the representational power, sampling efficiency and asymptotic correctness of SNFs on several benchmarks including applications to sampling molecular systems in equilibrium.
Forward citations
Cited by 5 Pith papers
-
Denoising Diffusion Probabilistic Models
Denoising diffusion probabilistic models generate high-quality images by learning to reverse a fixed forward diffusion process, achieving FID 3.17 on CIFAR10.
-
Stochastic Quantization as Optimal Control
Stochastic quantization is re-expressed as finite-time optimal control, in which a learned Doob force plus exact path weights reach the Gibbs measure without waiting for equilibrium.
-
Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory
Out-of-equilibrium simulations with open-to-periodic boundary switching plus a tailored stochastic normalizing flow enable efficient topology sampling in the continuum limit of four-dimensional SU(3) Yang-Mills theory.
-
Intrinsic Width of the Flux Tube as a tool to explore confining mechanisms in Lattice Gauge Theories
Lattice data on the intrinsic width of SU(2) flux tubes in 2+1D distinguish confining models, favoring dual superconductor at low T but with length-dependent Ginzburg-Landau parameter.
-
Continuously Tempered Diffusion Samplers
CTDS trains neural samplers with a controlled Langevin dynamics over both position and a continuous temperature coordinate, and reports improved sampling on a 40-mode Gaussian mixture.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.