Imagen de Portada

Deep Learning of Compositional Targets with Hierarchical Spectral Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tabanelli, Hugo, Dandi, Yatin, Pesce, Luca, Krzakala, Florent
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

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

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

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

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

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

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

A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
por: Dandi, Yatin, et al.
Publicado: (2024)

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

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

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

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

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

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

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

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model
por: Tabanelli, Hugo, et al.
Publicado: (2025)

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

A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning
por: Wadia, Neha S., et al.
Publicado: (2023)

Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method
por: Dandi, Yatin, et al.
Publicado: (2026)

A phase transition between positional and semantic learning in a solvable model of dot-product attention
por: Cui, Hugo, et al.
Publicado: (2024)

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

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

Analysis of learning a flow-based generative model from limited sample complexity
por: Cui, Hugo, et al.
Publicado: (2023)

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
por: Xu, Yizhou, et al.
Publicado: (2025)

Optimal scaling laws in learning hierarchical multi-index models
por: Defilippis, Leonardo, et al.
Publicado: (2026)

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
por: Defilippis, Leonardo, et al.
Publicado: (2026)

Fundamental limits of Non-Linear Low-Rank Matrix Estimation
por: Mergny, Pierre, et al.
Publicado: (2024)

Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers
por: Vilucchio, Matteo, et al.
Publicado: (2023)

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

Asymptotic Gaussian Fluctuations of Eigenvectors in Spectral Clustering
por: Lebeau, Hugo, et al.
Publicado: (2024)

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

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
por: Erba, Vittorio, et al.
Publicado: (2025)

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

Rigorous dynamical mean field theory for stochastic gradient descent methods
por: Gerbelot, Cedric, et al.
Publicado: (2022)

High-Dimensional Partial Least Squares: Spectral Analysis and Fundamental Limitations
por: Léger, Victor, et al.
Publicado: (2025)

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

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

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression
por: Clarté, Lucas, et al.
Publicado: (2024)

Sequential Group Composition: A Window into the Mechanics of Deep Learning
por: Marchetti, Giovanni Luca, et al.
Publicado: (2026)

FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet
por: Pautrel, Thibault, et al.
Publicado: (2026)