Image de couverture de livre

Universality of high-dimensional scaling limits of stochastic gradient descent

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Gheissari, Reza, Jagannath, Aukosh
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Probability Statistics Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Finding planted cliques using gradient descent
par: Gheissari, Reza, et autres
Publié: (2023)

Spectral alignment of stochastic gradient descent for high-dimensional classification tasks
par: Arous, Gerard Ben, et autres
Publié: (2023)

Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions
par: Arous, Gerard Ben, et autres
Publié: (2025)

Pseudo-Maximum Likelihood Theory for High-Dimensional Rank One Inference
par: Grant, Curtis, et autres
Publié: (2025)

Fast Spawn\&Prune (FS\&P): Global convergence of stochastic conic particle gradient descent via birth/death process
par: De Castro, Yohann, et autres
Publié: (2026)

High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance
par: Balasubramanian, Krishnakumar, et autres
Publié: (2023)

Joint stochastic localization and applications
par: Alberts, Tom, et autres
Publié: (2025)

Statistical limits of correlation detection in trees
par: Ganassali, Luca, et autres
Publié: (2022)

Stochastic gradient descent in high dimensions for multi-spiked tensor PCA
par: Arous, Gérard Ben, et autres
Publié: (2024)

One-step corrected projected stochastic gradient descent for statistical estimation
par: Brouste, Alexandre, et autres
Publié: (2023)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
par: Lytras, Iosif, et autres
Publié: (2025)

High dimensional analysis reveals conservative sharpening and a stochastic edge of stability
par: Agarwala, Atish, et autres
Publié: (2024)

Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes
par: Dereich, Steffen, et autres
Publié: (2021)

User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
par: Dalalyan, Arnak S., et autres
Publié: (2017)

High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models
par: Liang, Tengyuan, et autres
Publié: (2022)

On the distance between mean and geometric median in high dimensions
par: Schwank, Richard, et autres
Publié: (2025)

Universality of Kernel Random Matrices and Kernel Regression in the Quadratic Regime
par: Pandit, Parthe, et autres
Publié: (2024)

Achieving the Kesten-Stigum bound in the non-uniform hypergraph stochastic block model
par: Fernandez V, Manuel, et autres
Publié: (2026)

Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights
par: Balasubramanian, Krishnakumar, et autres
Publié: (2025)

A Fourier representation of kernel Stein discrepancy with application to Goodness-of-Fit tests for measures on infinite dimensional Hilbert spaces
par: Wynne, George, et autres
Publié: (2022)

Sharp detection of low-dimensional structure in probability measures via dimensional logarithmic Sobolev inequalities
par: Li, Matthew T. C., et autres
Publié: (2024)

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation
par: Mou, Wenlong, et autres
Publié: (2021)

On Universality of Non-Separable Approximate Message Passing Algorithms
par: Lovig, Max, et autres
Publié: (2025)

Samplet limits and multiwavelets
par: Giacchi, Gianluca, et autres
Publié: (2026)

Central limit theorems for high dimensional dependent data
par: Chang, Jinyuan, et autres
Publié: (2021)

High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile
par: Bigot, Jérémie, et autres
Publié: (2024)

Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms
par: Neufeld, Ariel, et autres
Publié: (2024)

High-dimensional ridge regression with random features for non-identically distributed data with a variance profile
par: Dabo, Issa-Mbenard, et autres
Publié: (2025)

Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
par: Dette, Holger, et autres
Publié: (2024)

Differentially private multivariate medians
par: Ramsay, Kelly, et autres
Publié: (2022)

High-accuracy log-concave sampling with stochastic queries
par: Chen, Fan, et autres
Publié: (2026)

Singular-limit analysis of gradient descent with noise injection
par: Shalova, Anna, et autres
Publié: (2024)

Spike-timing-dependent Hebbian learning as noisy gradient descent
par: Dexheimer, Niklas, et autres
Publié: (2025)

Statistical Inference for Linear Functionals of Online SGD in High-dimensional Linear Regression
par: Agrawalla, Bhavya, et autres
Publié: (2023)

Learning with Expected Signatures: Theory and Applications
par: Lucchese, Lorenzo, et autres
Publié: (2025)

Nonlinear Bayesian Update via Ensemble Kernel Regression with Clustering and Subsampling
par: Lee, Yoonsang
Publié: (2025)

Gradient-flow SDEs have unique transient population dynamics
par: Guan, Vincent, et autres
Publié: (2025)

On Experiments
par: van Rooyen, Brendan
Publié: (2025)

Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks
par: Rangriz, Parsa
Publié: (2025)

A variational approach to dimension-free self-normalized concentration
par: Chugg, Ben, et autres
Publié: (2025)