Copertina

Spring-block theory of feature learning in deep neural networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shi, Cheng, Pan, Liming, Dokmanić, Ivan
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Disordered Systems and Neural Networks Statistical Mechanics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the role of non-linear latent features in bipartite generative neural networks
di: Bonnaire, Tony, et al.
Pubblicazione: (2025)

Coding schemes in neural networks learning classification tasks
di: van Meegen, Alexander, et al.
Pubblicazione: (2024)

Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis
di: Lee, Donghee, et al.
Pubblicazione: (2024)

Microscopic and collective signatures of feature learning in neural networks
di: Corti, Andrea, et al.
Pubblicazione: (2025)

Weight fluctuations in (deep) linear neural networks and a derivation of the inverse-variance flatness relation
di: Gross, Markus, et al.
Pubblicazione: (2023)

Homophily modulates double descent generalization in graph convolution networks
di: Shi, Cheng, et al.
Pubblicazione: (2022)

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
di: Nguyen, Minh-Toan, et al.
Pubblicazione: (2026)

The autoregressive neural network architecture of the Boltzmann distribution of pairwise interacting spins systems
di: Biazzo, Indaco
Pubblicazione: (2023)

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
di: Ghio, Davide, et al.
Pubblicazione: (2023)

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
di: Ricci, Fabiola, et al.
Pubblicazione: (2026)

Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
di: Zhao, Yueqi, et al.
Pubblicazione: (2025)

Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation
di: Giorlandino, Alessio, et al.
Pubblicazione: (2025)

Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation
di: Barbier, Jean, et al.
Pubblicazione: (2025)

The committee machine: Computational to statistical gaps in learning a two-layers neural network
di: Aubin, Benjamin, et al.
Pubblicazione: (2018)

Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
di: Zou, Wenxuan, et al.
Pubblicazione: (2023)

Analytic theory of dropout regularization
di: Mori, Francesco, et al.
Pubblicazione: (2025)

Distinct mechanisms underlying in-context learning in transformers
di: Gibson, Cole, et al.
Pubblicazione: (2026)

Escape dynamics and implicit bias of one-pass SGD in overparameterized quadratic networks
di: Bocchi, Dario, et al.
Pubblicazione: (2026)

Machine learning the Ising transition: A comparison between discriminative and generative approaches
di: Zhang, Difei, et al.
Pubblicazione: (2024)

Discrete generative diffusion models without stochastic differential equations: a tensor network approach
di: Causer, Luke, et al.
Pubblicazione: (2024)

Phase determination with and without deep learning
di: Çivitcioğlu, Burak, et al.
Pubblicazione: (2024)

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
di: Barbier, Jean, et al.
Pubblicazione: (2025)

Statistical mechanics of extensive-width Bayesian neural networks near interpolation
di: Barbier, Jean, et al.
Pubblicazione: (2025)

Fundamental operating regimes, hyper-parameter fine-tuning and glassiness: towards an interpretable replica-theory for trained restricted Boltzmann machines
di: Fachechi, Alberto, et al.
Pubblicazione: (2024)

Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
di: Nartallo-Kaluarachchi, Ramón, et al.
Pubblicazione: (2026)

Phase transitions in the mini-batch size for sparse and dense two-layer neural networks
di: Marino, Raffaele, et al.
Pubblicazione: (2023)

Competing nonlinearities, criticality, and order-to-chaos transition in deep networks
di: Lesser, Omri, et al.
Pubblicazione: (2026)

Banded non-Hermitian random matrices, neural networks, and eigenvalue degeneracies
di: Huang, Richard, et al.
Pubblicazione: (2026)

Glassy dynamics in deep neural networks: A structural comparison
di: Winter, Max Kerr, et al.
Pubblicazione: (2024)

Dynamical stability for dense patterns in discrete attractor neural networks
di: Cohen, Uri, et al.
Pubblicazione: (2025)

General theory for extended-range percolation on simple and multiplex networks
di: Cirigliano, Lorenzo, et al.
Pubblicazione: (2024)

Dataset-learning duality and emergent criticality
di: Kukleva, Ekaterina, et al.
Pubblicazione: (2024)

Information content in continuous attractor neural networks is preserved in the presence of moderate disordered background connectivity
di: Kühn, Tobias, et al.
Pubblicazione: (2023)

Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
di: Ingrosso, Alessandro, et al.
Pubblicazione: (2024)

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
di: Ricci, Fabiola, et al.
Pubblicazione: (2025)

Predictive power of a Bayesian effective action for fully-connected one hidden layer neural networks in the proportional limit
di: Baglioni, P., et al.
Pubblicazione: (2024)

Sampling the space of solutions of an artificial neural network
di: Zambon, Alessandro, et al.
Pubblicazione: (2025)

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory
di: Mori, Francesco, et al.
Pubblicazione: (2024)

Transfer Learning in $\ell_1$ Regularized Regression: Hyperparameter Selection Strategy based on Sharp Asymptotic Analysis
di: Okajima, Koki, et al.
Pubblicazione: (2024)

Generalization vs. Specialization under Concept Shift
di: Nguyen, Alex, et al.
Pubblicazione: (2024)