Copertina

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Camilli, Francesco, Tieplova, Daria, Bergamin, Eleonora, Barbier, Jean
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Statistics Theory Disordered Systems and Neural Networks Information Theory Mathematical Physics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Information-theoretic limits and approximate message-passing for high-dimensional time series
di: Tieplova, Daria, et al.
Pubblicazione: (2025)

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

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

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

Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
di: Barbier, Jean, et al.
Pubblicazione: (2024)

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

On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance
di: Barbier, Jean, et al.
Pubblicazione: (2024)

Compressed sensing with l0-norm: statistical physics analysis and algorithms for signal recovery
di: Barbier, D., et al.
Pubblicazione: (2023)

Proportional asymptotics of piecewise exponential proportional hazards models
di: Massa, Emanuele
Pubblicazione: (2025)

A multiscale cavity method for sublinear-rank symmetric matrix factorization
di: Barbier, Jean, et al.
Pubblicazione: (2024)

BBP transition and the leading eigenvector of the spiked Wigner model with inhomogeneous noise
di: Ferreira, Leonardo S., et al.
Pubblicazione: (2026)

Role of Bootstrap Averaging in Generalized Approximate Message Passing
di: Takahashi, Takashi
Pubblicazione: (2023)

Replica Analysis for Ensemble Techniques in Variable Selection
di: Takahashi, Takashi
Pubblicazione: (2024)

The replica-symmetric free energy for Ising spin glasses with orthogonally invariant couplings
di: Fan, Zhou, et al.
Pubblicazione: (2021)

Some observations on the ambivalent role of symmetries in Bayesian inference problems
di: Semerjian, Guilhem
Pubblicazione: (2025)

Matrix denoising: Bayes-optimal estimators via low-degree polynomials
di: Semerjian, Guilhem
Pubblicazione: (2024)

How to escape atypical regions in the symmetric binary perceptron: a journey through connected-solutions states
di: Barbier, Damien
Pubblicazione: (2024)

Generalization performance of narrow one-hidden layer networks in the teacher-student setting
di: Ortiz, Rodrigo Pérez, et al.
Pubblicazione: (2025)

The phase diagram of compressed sensing with $\ell_0$-norm regularization
di: Barbier, Damien, et al.
Pubblicazione: (2024)

Ground state energies of multipartite $p$-spin models -- partially lifted RDT view
di: Stojnic, Mihailo
Pubblicazione: (2025)

The twin peaks of learning neural networks
di: Demyanenko, Elizaveta, et al.
Pubblicazione: (2024)

Explicit mutual information for simple networks and neurons with lognormal activities
di: Chwiłka, Maurycy, et al.
Pubblicazione: (2023)

Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
di: Cavaliere, Angelo Giorgio, et al.
Pubblicazione: (2025)

Analysis of Diffusion Models for Manifold Data
di: George, Anand Jerry, et al.
Pubblicazione: (2025)

Networks of neural networks: more is different
di: Agliari, Elena, et al.
Pubblicazione: (2025)

A theoretical perspective on mode collapse in variational inference
di: Soletskyi, Roman, et al.
Pubblicazione: (2024)

High-dimensional manifold of solutions in neural networks: insights from statistical physics
di: Malatesta, Enrico M.
Pubblicazione: (2023)

Observable asymptotics of regularized Cox regression models with standard Gaussian designs: a statistical mechanics approach
di: Massa, Emanuele, et al.
Pubblicazione: (2024)

Explosive neural networks via higher-order interactions in curved statistical manifolds
di: Aguilera, Miguel, et al.
Pubblicazione: (2024)

On the supra-linear storage in dense networks of grid and place cells
di: Barra, Adriano, et al.
Pubblicazione: (2025)

Spectra of random graphs with discrete scale invariance
di: Catanzaro, Alessio, et al.
Pubblicazione: (2025)

A Physical Theory of Two-stage Thermalization
di: Jonay, Cheryne, et al.
Pubblicazione: (2023)

Random-Energy Secret Sharing via Extreme Synergy
di: Ngampruetikorn, Vudtiwat, et al.
Pubblicazione: (2023)

High-dimensional random landscapes: from typical to large deviations
di: Ros, Valentina
Pubblicazione: (2025)

Fixed width treelike neural networks capacity analysis -- generic activations
di: Stojnic, Mihailo
Pubblicazione: (2024)

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
di: Stojnic, Mihailo
Pubblicazione: (2024)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
di: Maillard, Antoine, et al.
Pubblicazione: (2024)

Critical exponents at the Nishimori point
di: Delfino, Gesualdo
Pubblicazione: (2024)

Exact results for spin glass criticality
di: Delfino, Gesualdo
Pubblicazione: (2025)

A Tale of Two Uplifts: Parisi-Sourlas with Defects
di: Ghosh, Kausik, et al.
Pubblicazione: (2025)