Cover Image

The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dandi, Yatin, Troiani, Emanuele, Arnaboldi, Luca, Pesce, Luca, Zdeborová, Lenka, Krzakala, Florent
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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)

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

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

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

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

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

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

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

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

Universality laws for Gaussian mixtures in generalized linear models
by: Dandi, Yatin, 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)

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

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

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

Gibbs Sampling the Posterior of Neural Networks
by: Piccioli, Giovanni, et al.
Published: (2023)

Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
by: Boncoraglio, Fabrizio, et al.
Published: (2025)

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

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

Maximally-stable Local Optima in Random Graphs and Spin Glasses: Phase Transitions and Universality
by: Dandi, Yatin, et al.
Published: (2023)

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

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
by: Defilippis, Leonardo, et al.
Published: (2025)

Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens
by: Erba, Vittorio, et al.
Published: (2024)

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

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

Optimal Spectral Transitions in High-Dimensional Multi-Index Models
by: Defilippis, Leonardo, 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)

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

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

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

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

Sequential Dynamics in Ising Spin Glasses
by: Dandi, Yatin, et al.
Published: (2025)

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

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

Bayes optimal learning of attention-indexed models
by: Boncoraglio, Fabrizio, et al.
Published: (2025)

Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers
by: Behrens, Freya, et al.
Published: (2024)

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

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

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