Cover Image

Random Matrix Theory of Early-Stopped Gradient Flow: A Transient BBP Scenario

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Coeurdoux, Florentin, Ferré, Grégoire, Bouchaud, Jean-Philippe
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Holdout cross-validation for large non-Gaussian covariance matrix estimation using Weingarten calculus
by: Lamrani, Lamia, et al.
Published: (2025)

Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent
by: Patil, Pratik, et al.
Published: (2024)

Probing the Geometry of Diffusion Models with the String Method
by: Moreau, Elio, et al.
Published: (2026)

Convex SGD: Generalization Without Early Stopping
by: Hendrickx, Julien, et al.
Published: (2024)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
by: Yang, Yingzhen, et al.
Published: (2024)

Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression
by: Wegel, Tobias, et al.
Published: (2025)

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

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

Early Stopping in Contextual Bandits and Inferences
by: Cui, Zihan
Published: (2025)

On Regularization via Early Stopping for Least Squares Regression
by: Sonthalia, Rishi, et al.
Published: (2024)

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

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
by: Aolaritei, Liviu, et al.
Published: (2025)

Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
by: Annesi, Brandon Livio, et al.
Published: (2025)

Statistical Inference on Gradient Flows
by: Li, Tongyu, et al.
Published: (2026)

Optimal Confidence Band for Kernel Gradient Flow Estimator
by: Cheng, Yuqian, et al.
Published: (2026)

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

On Stopping Times of Power-one Sequential Tests: Tight Lower and Upper Bounds
by: Agrawal, Shubhada, et al.
Published: (2025)

Gradient Equilibrium in Online Learning: Theory and Applications
by: Angelopoulos, Anastasios N., et al.
Published: (2025)

Generalization Bounds and Stopping Rules for Learning with Self-Selected Data
by: Rodemann, Julian, et al.
Published: (2025)

Signal-Plus-Noise Decomposition of Nonlinear Spiked Random Matrix Models
by: Moniri, Behrad, et al.
Published: (2024)

Precise analysis of ridge interpolators under heavy correlations -- a Random Duality Theory view
by: Stojnic, Mihailo
Published: (2024)

Exogenous Randomness Empowering Random Forests
by: Mei, Tianxing, et al.
Published: (2024)

Predictive Inference in Multi-environment Scenarios
by: Duchi, John C., et al.
Published: (2024)

A Stein Gradient Descent Approach for Doubly Intractable Distributions
by: Lee, Heesang, et al.
Published: (2024)

Learning with Differentially Private (Sliced) Wasserstein Gradients
by: Rodríguez-Vítores, David, et al.
Published: (2025)

On the Natural Gradient of the Evidence Lower Bound
by: Ay, Nihat, et al.
Published: (2023)

Online Statistical Inference in Decision-Making with Matrix Context
by: Han, Qiyu, et al.
Published: (2022)

Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
by: Cai, T. Tony, et al.
Published: (2026)

A Theory of Universal Agnostic Learning
by: Hanneke, Steve, et al.
Published: (2026)

Stacked SVD or SVD stacked? A Random Matrix Theory perspective on data integration
by: Baharav, Tavor Z., et al.
Published: (2025)

Statistics of Min-max Normalized Eigenvalues in Random Matrices
by: Nakada, Hyakka, et al.
Published: (2025)

Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components
by: Shi, Naichen, et al.
Published: (2024)

Gradient descent for deep equilibrium single-index models
by: Dandapanthula, Sanjit, et al.
Published: (2025)

Finite-Particle Rates for Regularized Stein Variational Gradient Descent
by: He, Ye, et al.
Published: (2026)

Gradient dynamics for low-rank fine-tuning beyond kernels
by: Dayi, Arif Kerem, et al.
Published: (2024)

On the Contractivity of Stochastic Interpolation Flow
by: Daniels, Mara
Published: (2025)

Structured Matrix Learning under Arbitrary Entrywise Dependence and Estimation of Markov Transition Kernel
by: Chai, Jinhang, et al.
Published: (2024)

Interactive Learning of Single-Index Models via Stochastic Gradient Descent
by: Rajaraman, Nived, et al.
Published: (2026)

Gradient-enhanced global sensitivity analysis with Poincar{é} chaos expansions
by: Roustant, O, et al.
Published: (2025)

Early stopping and polynomial smoothing in regression with reproducing kernels
by: Averyanov, Yaroslav, et al.
Published: (2020)