Pith. sign in

REVIEW 6 cited by

Equivariant Flows: sampling configurations for multi-body systems with symmetric energies

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 1910.00753 v1 pith:TA5E6T66 submitted 2019-10-02 stat.ML cs.LGphysics.chem-phphysics.comp-ph

classification stat.MLcs.LGphysics.chem-phphysics.comp-ph
keywords flowsequivariantconfigurationsdistributiongeneralizeprobabilitysamplessampling
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Flows are exact-likelihood generative neural networks that transform samples from a simple prior distribution to the samples of the probability distribution of interest. Boltzmann Generators (BG) combine flows and statistical mechanics to sample equilibrium states of strongly interacting many-body systems such as proteins with 1000 atoms. In order to scale and generalize these results, it is essential that the natural symmetries of the probability density - in physics defined by the invariances of the energy function - are built into the flow. Here we develop theoretical tools for constructing such equivariant flows and demonstrate that a BG that is equivariant with respect to rotations and particle permutations can generalize to sampling nontrivially new configurations where a nonequivariant BG cannot.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Fast and Distributed Equivariant Graph Neural Networks by Virtual Node Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    FastEGNN and DistEGNN use ordered, learnable virtual nodes with an MMD alignment loss to make equivariant GNNs accurate on sparse and distributed large geometric graphs.

  2. A Data-Driven Method for Modeling Creep-Fatigue Stress-Strain Behavior Using Neural ODEs

    physics.comp-ph 2025-05 conditional novelty 6.0 of 10

    Neural ODE models trained on 19 experimental creep-fatigue tests of Alloy 617 reproduce stress-strain loops better than the standard Chaboche model, and symbolic regression converts one into an interpretable polynomial.

  3. JFlow: Model-Independent Spherical Jeans Analysis using Equivariant Continuous Normalizing Flows

    astro-ph.GA 2025-05 conditional novelty 6.0 of 10

    JFlow uses equivariant continuous normalizing flows and kernel-density-estimated projected likelihoods to perform model-independent spherical Jeans analysis, recovering dark matter mass densities in a mock dwarf spher...

  4. Accurate and thermodynamically consistent hydrogen equation of state for planetary modeling with flow matching

    astro-ph.EP 2025-01 conditional novelty 6.0 of 10

    Flow matching benchmarks thermodynamic integration for dense hydrogen, exposes a thermodynamic inconsistency in the REOS3 equation of state, and yields a new Jupiter adiabat.

  5. Discovery of Spin-Crossover Candidates with Equivariant Graph Neural Networks and Relevance-Based Classification

    cond-mat.dis-nn 2025-01 conditional novelty 6.0 of 10

    An equivariant graph neural network predicts spin-crossover energies for thousands of metal complexes and enriches candidate detection about four-fold over random screening.

  6. Scaling of Stochastic Normalizing Flows in $\mathrm{SU}(3)$ lattice gauge theory

    hep-lat 2024-11 conditional novelty 6.0 of 10

    First demonstration that Stochastic Normalizing Flows inherit the linear-with-volume scaling of non-equilibrium MCMC in 4D SU(3) lattice gauge theory, with a factor-of-two efficiency gain.

Pith tools