Metraipolis › archive › dc_2b192e65ac5f
Deep Learning Theory through the Lens of Statistical Physics: A Topical Review — arXiv:2611.09138
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09138
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:41:27.192Z
- SHA-256 of the archived text
c1cd0012e84e65f4f104057643d118a7c18f7aca15ff3f6e766b1dc71b9dab2e- Stable URL of this page
https://metraipolis.com/documento/dc_2b192e65ac5f
How to cite
Deep Learning Theory through the Lens of Statistical Physics: A Topical Review — arXiv:2611.09138 — arXiv (en), https://arxiv.org/abs/2611.09138 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b192e65ac5f (Metraipolis archive dc_2b192e65ac5f, sha256 c1cd0012e84e65f4f104057643d118a7c18f7aca15ff3f6e766b1dc71b9dab2e)
BibTeX
@misc{dc2b192e65ac5f,
title = {Deep Learning Theory through the Lens of Statistical Physics: A Topical Review — arXiv:2611.09138},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09138},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b192e65ac5f; sha256 c1cd0012e84e65f4f104057643d118a7c18f7aca15ff3f6e766b1dc71b9dab2e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09138. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The recent success of foundation models and deep learning has far outpaced our theoretical understanding of how large-scale neural networks learn and generalize. Statistical physics provides a natural language for describing such high-dimensional, nonlinear, and strongly coupled systems, offering concepts such as mean-field theory, phase transitions, energy landscapes, and stochastic dynamics. In this topical review, we adopt a statistical-physics way of thinking -- from concepts including phases and criticality, and free-energy viewpoints, to methods such as kernel and Gaussian-process limits, mean-field and dynamical mean-field theories, random-matrix tools, and Fokker-Planck formalisms, and to a mindset emphasizing universality, scaling, and tractable limits with explicit validity regimes. We survey recent progress on understanding modern deep learning through this lens, including mean-field analyses of wide networks, spectral and geometric perspectives on loss landscapes, stochastic-gradient-based training viewed as a dynamical process, and phase-transition analogies that organize phenomena such as overparameterization, generalization, and representation change. Our goal is to synthesize these threads into a coherent framework that clarifies what each approximation explains, when it is expected to hold, and how apparently competing narratives relate or diverge. Together, these perspectives form a unified physical framework that views representation learning as a collective phenomenon in high-dimensional systems, bridging deterministic and stochastic regimes of gradient-based optimization. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Statistical Mechanics (cond-mat.stat-mech). Pagina del lavoro: https://arxiv.org/abs/2611.09138 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:33:47.153Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).