Cover Image

Large Spikes in Stochastic Gradient Descent: A Large-Deviations View

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gess, Benjamin, Heydecker, Daniel
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Probability Primary 68T05, 60F10, Secondary 60J05, 37H15, 68Q32
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Sample completion, structured correlation, and Netflix problems
by: Coregliano, Leonardo N., et al.
Published: (2025)

Central limit theorems for additive functionals in patricia tries
by: Ischebeck, Jasper
Published: (2023)

Limit theorems for fixed point biased permutations avoiding a pattern of length three
by: Chelikavada, Aksheytha, et al.
Published: (2023)

High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models
by: Fan, Zhou, et al.
Published: (2026)

A cohesive account on the ergodic behaviours and scaling limits of Random Walks in Cooling Random Environments
by: Avena, Luca, et al.
Published: (2026)

Generalized delayed Black and Scholes Formula
by: Golé, Hubert Le Bi, et al.
Published: (2025)

Harnack Inequalities and Ergodicity of Stochastic Reaction-Diffusion Equation in $L^p$
by: Liu, Zhihui
Published: (2020)

An Exponential Averaging Process with Strong Convergence Properties
by: Köhne, Frederik, et al.
Published: (2025)

High-arity PAC learning via exchangeability
by: Coregliano, Leonardo N., et al.
Published: (2024)

Large Deviations and the Peano Phenomenon in Stochastic Differential Equations with Homogeneous Drift
by: Bermolen, Paola, et al.
Published: (2025)

Jump Processes with Self-Interactions: Large Deviation Asymptotics
by: Budhiraja, Amarjit, et al.
Published: (2025)

Fibonacci-Driven Recursive Ensembles: Algorithms, Convergence, and Learning Dynamics
by: Fokoué, Ernest
Published: (2026)

On fine fluctuations of the complexity of the QuickSelect algorithm
by: Ischebeck, Jasper, et al.
Published: (2024)

Set-valued recursions arising from vantage-point trees
by: Dong, Congzao, et al.
Published: (2023)

Rates of convergence for multivariate SDEs driven by Lévy processes in the small-time stable domain of attraction
by: Cázares, Jorge González, et al.
Published: (2025)

Perpetuities with light tails and the local dependence measure
by: Bihan, Julia Le, et al.
Published: (2025)

A quantitative central limit theorem for the simple symmetric exclusion process
by: Gess, Benjamin, et al.
Published: (2024)

Large and moderate deviations for Gaussian neural networks
by: Macci, Claudio, et al.
Published: (2024)

Asymptotic Log-Harnack Inequality for Monotone SPDE with Multiplicative Noise
by: Liu, Zhihui
Published: (2020)

Law of the Iterated Logarithm for Markov Semigroups with Exponential Mixing in the Wasserstein Distance
by: Czapla, Dawid, et al.
Published: (2025)

Multiple consecutive runs of multi-state trials: distributions of $(k_1, k_2, \dots, k_\ell)$ patterns
by: Kong, Yong
Published: (2024)

On the large-time behaviour of affine Volterra processes
by: Jacquier, Antoine, et al.
Published: (2022)

A central limit theorem for the stochastic cable equation
by: Nishino, Soma
Published: (2025)

Moderate Deviations for a Stochastic Schrödinger Equation with Linear Drift
by: Fatheddin, Parisa, et al.
Published: (2023)

Stochastic limits of Quantum repeated measurements
by: Jacquier, Antoine, et al.
Published: (2025)

The record statistic and forward stability of Schubert products
by: Hardt, Andrew, et al.
Published: (2026)

Convergence Analysis of Real-time Recurrent Learning (RTRL) for a class of Recurrent Neural Networks
by: Lam, Samuel Chun-Hei, et al.
Published: (2025)

Kernel Limit for a Class of Recurrent Neural Networks Trained on Ergodic Data Sequences
by: Lam, Samuel Chun-Hei, et al.
Published: (2023)

Cutoff Phenomenon for Inhomogeneous Nonlinear Recombination in Arbitrary Finite Product Spaces
by: Kim, Junho, et al.
Published: (2025)

Sampling elements of a finite group: efficiency of the product replacement algorithm with an accumulator
by: Marcinkowski, Michał, et al.
Published: (2025)

Random Markov property for random walks in random environments
by: Allasia, Julien, et al.
Published: (2024)

Parameter estimation for the stochastic heat equation with multiplicative noise from local measurements
by: Janák, Josef, et al.
Published: (2023)

Convergence of blanket times for sequences of random walks on critical random graphs
by: Andriopoulos, George
Published: (2018)

Statistics for the triangle density in ERGM and its mean-field approximation
by: Magnanini, Elena, et al.
Published: (2024)

Large deviations of one-hidden-layer neural networks
by: Hirsch, Christian, et al.
Published: (2024)

Marginal dynamics of probabilistic cellular automata on trees
by: Lacker, Daniel, et al.
Published: (2025)

Markov Chain Gradient Descent in Hilbert Spaces
by: Roy, Priyanka, et al.
Published: (2024)

Superdiffusive planar random walks with polynomial space-time drifts
by: da Costa, Conrado, et al.
Published: (2024)

Limit theorems for the number of crossings and stress in projections of the random geometric graph
by: Döring, Hanna, et al.
Published: (2024)

Existence of a plane without edge crossings in projections of the random geometric graph
by: de Jonge, Lianne, et al.
Published: (2025)