Pith. sign in

REVIEW 1 cited by

Cascade of phase transitions in the training of Energy-based models

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 2405.14689 v4 pith:4TI6RN3H submitted 2024-05-23 cs.LG cond-mat.dis-nncond-mat.stat-mech

classification cs.LGcond-mat.dis-nncond-mat.stat-mech
keywords phasetransitionsanalyticallydatafirstmodelmodesreal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we investigate the feature encoding process in a prototypical energy-based generative model, the Restricted Boltzmann Machine (RBM). We start with an analytical investigation using simplified architectures and data structures, and end with numerical analysis of real trainings on real datasets. Our study tracks the evolution of the model's weight matrix through its singular value decomposition, revealing a series of phase transitions associated to a progressive learning of the principal modes of the empirical probability distribution. The model first learns the center of mass of the modes and then progressively resolve all modes through a cascade of phase transitions. We first describe this process analytically in a controlled setup that allows us to study analytically the training dynamics. We then validate our theoretical results by training the Bernoulli-Bernoulli RBM on real data sets. By using data sets of increasing dimension, we show that learning indeed leads to sharp phase transitions in the high-dimensional limit. Moreover, we propose and test a mean-field finite-size scaling hypothesis. This shows that the first phase transition is in the same universality class of the one we studied analytically, and which is reminiscent of the mean-field paramagnetic-to-ferromagnetic phase transition.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Parallel Trajectory Tempering with reservoirs and adaptive steps makes equilibrium maximum-likelihood training of EBMs practical and often better than PCD and deep generators on multimodal scientific data.

Pith tools