Cover Image

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dandi, Yatin, Pesce, Luca, Cui, Hugo, Krzakala, Florent, Lu, Yue M., Loureiro, Bruno
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model
by: Wortsman-Zurich, Arie, et al.
Published: (2026)

Universality laws for Gaussian mixtures in generalized linear models
by: Dandi, Yatin, et al.
Published: (2023)

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

Deep Learning of Compositional Targets with Hierarchical Spectral Methods
by: Tabanelli, Hugo, et al.
Published: (2026)

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
by: Dandi, Yatin, et al.
Published: (2023)

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs
by: Arnaboldi, Luca, et al.
Published: (2024)

The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent
by: Dandi, Yatin, et al.
Published: (2025)

Asymptotics of Learning with Deep Structured (Random) Features
by: Schröder, Dominik, et al.
Published: (2024)

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

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

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions
by: Arnaboldi, Luca, et al.
Published: (2024)

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

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
by: Dandi, Yatin, et al.
Published: (2024)

Optimal Spectral Transitions in High-Dimensional Multi-Index Models
by: Defilippis, Leonardo, et al.
Published: (2025)

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining
by: Ren, Yunwei, et al.
Published: (2026)

Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds
by: Troiani, Emanuele, et al.
Published: (2025)

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula
by: Vilucchio, Matteo, et al.
Published: (2025)

Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime
by: Hu, Hong, et al.
Published: (2024)

Fundamental computational limits of weak learnability in high-dimensional multi-index models
by: Troiani, Emanuele, et al.
Published: (2024)

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

Generalization in Representation Models via Random Matrix Theory: Application to Recurrent Networks
by: Moakher, Yessin, et al.
Published: (2025)

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

Low-rank Matrix Estimation with Inhomogeneous Noise
by: Guionnet, Alice, et al.
Published: (2022)

Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
by: Xu, Yizhou, et al.
Published: (2025)

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

Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario
by: Coeurdoux, Florentin, et al.
Published: (2026)

Asymptotic Theory of Eigenvectors for Latent Embeddings with Generalized Laplacian Matrices
by: Fan, Jianqing, et al.
Published: (2025)

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

A Random Matrix Perspective of Echo State Networks: From Precise Bias--Variance Characterization to Optimal Regularization
by: Moakher, Yessin, et al.
Published: (2025)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
by: Firdoussi, Aymane El, et al.
Published: (2024)

Intrinsic Bayesian Cramér-Rao Bound with an Application to Covariance Matrix Estimation
by: Bouchard, Florent, et al.
Published: (2023)

Characterizing the Generalization Error of Random Feature Regression with Arbitrary Data-Augmentation
by: Morisset, Lucas, et al.
Published: (2026)

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
by: Liang, Tengyuan, et al.
Published: (2022)

Non-Asymptotic Analysis of Data Augmentation for Precision Matrix Estimation
by: Morisset, Lucas, et al.
Published: (2025)

Asymptotic Theory of Geometric and Adaptive $k$-Means Clustering
by: Jaffe, Adam Quinn
Published: (2022)

Theory and applications of the Sum-Of-Squares technique
by: Bach, Francis, et al.
Published: (2023)

Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
by: Arnaboldi, Luca, et al.
Published: (2023)

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

Adaptive Lasso, Transfer Lasso, and Beyond: An Asymptotic Perspective
by: Takada, Masaaki, et al.
Published: (2023)

Asymptotic Theory and Phase Transitions for Variable Importance in Quantile Regression Forests
by: Nakamura, Tomoshige, et al.
Published: (2025)