The thermodynamic limit in mean field neural networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917776660103168 |
|---|---|
| author | Agliari, Elena Barra, Adriano Bianco, Pierluigi Fachechi, Alberto Pallara, Diego |
| author_facet | Agliari, Elena Barra, Adriano Bianco, Pierluigi Fachechi, Alberto Pallara, Diego |
| contents | In the last five decades, mean-field neural-networks have played a crucial role in modelling associative memories and, in particular, the Hopfield model has been extensively studied using tools borrowed from the statistical mechanics of spin glasses. However, achieving mathematical control of the infinite-volume limit of the model's free-energy has remained elusive, as the standard treatments developed for spin-glasses have proven unfeasible. Here we address this long-standing problem by proving that a measure-concentration assumption for the order parameters of the theory is sufficient for the existence of the asymptotic limit of the model's free energy. The proof leverages the equivalence between the free energy of the Hopfield model and a linear combination of the free energies of a hard and a soft spin-glass, whose thermodynamic limits are rigorously known. Our work focuses on the replica-symmetry level of description (for which we recover the explicit expression of the free-energy found in the eighties via heuristic methods), yet, our scheme is expected to work also under (at least) the first step of replica symmetry breaking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10145 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The thermodynamic limit in mean field neural networks Agliari, Elena Barra, Adriano Bianco, Pierluigi Fachechi, Alberto Pallara, Diego Disordered Systems and Neural Networks Mathematical Physics In the last five decades, mean-field neural-networks have played a crucial role in modelling associative memories and, in particular, the Hopfield model has been extensively studied using tools borrowed from the statistical mechanics of spin glasses. However, achieving mathematical control of the infinite-volume limit of the model's free-energy has remained elusive, as the standard treatments developed for spin-glasses have proven unfeasible. Here we address this long-standing problem by proving that a measure-concentration assumption for the order parameters of the theory is sufficient for the existence of the asymptotic limit of the model's free energy. The proof leverages the equivalence between the free energy of the Hopfield model and a linear combination of the free energies of a hard and a soft spin-glass, whose thermodynamic limits are rigorously known. Our work focuses on the replica-symmetry level of description (for which we recover the explicit expression of the free-energy found in the eighties via heuristic methods), yet, our scheme is expected to work also under (at least) the first step of replica symmetry breaking. |
| title | The thermodynamic limit in mean field neural networks |
| topic | Disordered Systems and Neural Networks Mathematical Physics |
| url | https://arxiv.org/abs/2409.10145 |