Restricted Boltzmann machines (RBMs) constitute one of the main models for machine statistical inference and they are widely employed in artificial intelligence as powerful tools for (deep) learning. However, in contrast with countless remarkable practical successes, their mathematical formalization has been largely elusive: from a statistical-mechanics perspective these systems display the same (random) Gibbs measure of bi-partite spin-glasses, whose rigorous treatment is notoriously dicult.In this work, beyond providing a brief review on RBMs from both the learning and the retrieval perspectives, we aim to contribute to their analytical investigation, by considering two distinct realizations of their weights (i.e. Boolean and Gaussian) and studying the properties of their related free energies. More precisely, focusing on a RBM characterized by digital couplings, we first extend the Pastur–Shcherbina–Tirozzi method (originally developed for the Hopfield model) to prove the self-averaging property for the free energy, over its quenched expectation, in the infinite volume limit, then we explicitly calculate its simplest approximation, namely its annealed bound. Next, focusing on a RBM characterized by analogical weights, we extend Guerra’s interpolating scheme to obtain a control of the quenched free-energy under the assumption of replica symmetry (i.e. we require that the order parameters do not fluctuate in the thermodynamic limit): we get self-consistencies for the order parameters (in full agreement with the existing literature) as well as the critical line for ergodicity breaking that turns out to be the same obtained in AGS theory. As we discuss, this analogy stems from the slow-noise universality.Finally, glancing beyond replica symmetry, we analyze the fluctuations of the overlaps for a correct estimation of the (slow) noise aecting the retrieval of the signal, and by a stability analysis we recover the Aizenman–Contucci identities typical of glassy systems.

Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit / Agliari, Elena; Barra, Adriano; Tirozzi, Brunello. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - 2019:3(2019), p. 033301. [10.1088/1742-5468/ab02ef]

Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit

Agliari, Elena
;
Barra, Adriano;
2019

Abstract

Restricted Boltzmann machines (RBMs) constitute one of the main models for machine statistical inference and they are widely employed in artificial intelligence as powerful tools for (deep) learning. However, in contrast with countless remarkable practical successes, their mathematical formalization has been largely elusive: from a statistical-mechanics perspective these systems display the same (random) Gibbs measure of bi-partite spin-glasses, whose rigorous treatment is notoriously dicult.In this work, beyond providing a brief review on RBMs from both the learning and the retrieval perspectives, we aim to contribute to their analytical investigation, by considering two distinct realizations of their weights (i.e. Boolean and Gaussian) and studying the properties of their related free energies. More precisely, focusing on a RBM characterized by digital couplings, we first extend the Pastur–Shcherbina–Tirozzi method (originally developed for the Hopfield model) to prove the self-averaging property for the free energy, over its quenched expectation, in the infinite volume limit, then we explicitly calculate its simplest approximation, namely its annealed bound. Next, focusing on a RBM characterized by analogical weights, we extend Guerra’s interpolating scheme to obtain a control of the quenched free-energy under the assumption of replica symmetry (i.e. we require that the order parameters do not fluctuate in the thermodynamic limit): we get self-consistencies for the order parameters (in full agreement with the existing literature) as well as the critical line for ergodicity breaking that turns out to be the same obtained in AGS theory. As we discuss, this analogy stems from the slow-noise universality.Finally, glancing beyond replica symmetry, we analyze the fluctuations of the overlaps for a correct estimation of the (slow) noise aecting the retrieval of the signal, and by a stability analysis we recover the Aizenman–Contucci identities typical of glassy systems.
2019
neuronal networks; rigorous results in statistical mechanics; learning theory
01 Pubblicazione su rivista::01a Articolo in rivista
Free energies of Boltzmann machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit / Agliari, Elena; Barra, Adriano; Tirozzi, Brunello. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - 2019:3(2019), p. 033301. [10.1088/1742-5468/ab02ef]
File allegati a questo prodotto
File Dimensione Formato  
Agliari_Free-energies_2019.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.55 MB
Formato Adobe PDF
1.55 MB Adobe PDF   Contatta l'autore
Agliari_preprint_Free-energies_2019.pdf

accesso aperto

Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 253.53 kB
Formato Adobe PDF
253.53 kB Adobe PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1259545
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 10
  • ???jsp.display-item.citation.isi??? 10
social impact