Copertina

Asymptotics of Learning with Deep Structured (Random) Features

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Schröder, Dominik, Dmitriev, Daniil, Cui, Hugo, Loureiro, Bruno
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Disordered Systems and Neural Networks Statistics Theory
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
di: Vilucchio, Matteo, et al.
Pubblicazione: (2024)

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
di: Adomaityte, Urte, et al.
Pubblicazione: (2023)

Gaussian Universality of Perceptrons with Random Labels
di: Gerace, Federica, et al.
Pubblicazione: (2022)

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

Asymmetric Scaling Laws from Sparse Features
di: Sous, John, et al.
Pubblicazione: (2026)

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
di: Adomaityte, Urte, et al.
Pubblicazione: (2023)

Asymptotics of feature learning in two-layer networks after one gradient-step
di: Cui, Hugo, et al.
Pubblicazione: (2024)

High-dimensional Asymptotics of Denoising Autoencoders
di: Cui, Hugo, et al.
Pubblicazione: (2023)

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models
di: Mergny, Pierre, et al.
Pubblicazione: (2024)

Statistical Mechanics of Min-Max Problems
di: Ichikawa, Yuma, et al.
Pubblicazione: (2024)

Kernel Density Estimators in Large Dimensions
di: Biroli, Giulio, et al.
Pubblicazione: (2024)

Variational Gaussian Approximation in Replica Analysis of Parametric Models
di: Takahashi, Takashi
Pubblicazione: (2025)

Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares
di: Mergny, Pierre, et al.
Pubblicazione: (2025)

Generalization Dynamics of Linear Diffusion Models
di: Merger, Claudia, et al.
Pubblicazione: (2025)

Ratio Divergence Learning Using Target Energy in Restricted Boltzmann Machines: Beyond Kullback--Leibler Divergence Learning
di: Ishida, Yuichi, et al.
Pubblicazione: (2024)

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
di: Arnaboldi, Luca, et al.
Pubblicazione: (2025)

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

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
di: Takahashi, Takashi
Pubblicazione: (2022)

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
di: Favero, Alessandro
Pubblicazione: (2025)

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

Precise asymptotic analysis of Sobolev training for random feature models
di: Fisher, Katharine E, et al.
Pubblicazione: (2025)

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

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

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
di: Dandi, Yatin, et al.
Pubblicazione: (2026)

High-Dimensional Learning Dynamics of Quantized Models with Straight-Through Estimator
di: Ichikawa, Yuma, et al.
Pubblicazione: (2025)

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

Dimension-free deterministic equivalents and scaling laws for random feature regression
di: Defilippis, Leonardo, et al.
Pubblicazione: (2024)

Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
di: Ghosh, Subhroshekhar, et al.
Pubblicazione: (2026)

Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks
di: Tamai, Keiichi, et al.
Pubblicazione: (2023)

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks
di: Huang, Jie, et al.
Pubblicazione: (2026)

Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions
di: Bae, Jaeyong, et al.
Pubblicazione: (2024)

High-dimensional learning of narrow neural networks
di: Cui, Hugo
Pubblicazione: (2024)

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs
di: Tanner, Kasimir, et al.
Pubblicazione: (2024)

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

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

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

Limits of message passing for node classification: How class-bottlenecks restrict signal-to-noise ratio
di: Rubin, Jonathan, et al.
Pubblicazione: (2025)

Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
di: Annesi, Brandon Livio, 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)

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