Pith. sign in

REVIEW 1 cited by

A duality connecting neural network and cosmological dynamics

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 2202.11104 v1 pith:5KNDBHYN submitted 2022-02-22 gr-qc astro-ph.COcs.LGhep-phhep-th

A duality connecting neural network and cosmological dynamics

classification gr-qc astro-ph.COcs.LGhep-phhep-th
keywords dynamicsneuraldualitynetworkcosmologicaldescentfieldgradient
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We demonstrate that the dynamics of neural networks trained with gradient descent and the dynamics of scalar fields in a flat, vacuum energy dominated Universe are structurally profoundly related. This duality provides the framework for synergies between these systems, to understand and explain neural network dynamics and new ways of simulating and describing early Universe models. Working in the continuous-time limit of neural networks, we analytically match the dynamics of the mean background and the dynamics of small perturbations around the mean field, highlighting potential differences in separate limits. We perform empirical tests of this analytic description and quantitatively show the dependence of the effective field theory parameters on hyperparameters of the neural network. As a result of this duality, the cosmological constant is matched inversely to the learning rate in the gradient descent update.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

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

  1. Bulk-boundary decomposition of neural networks

    cs.LG 2025-11 reject novelty 3.0

    The paper reframes SGD training of deep networks as a local Lagrangian with data confined to the boundaries, but the advertised energy continuity equation is absent from the body.