Image de couverture de livre

Analysing heavy-tail properties of Stochastic Gradient Descent by means of Stochastic Recurrence Equations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Damek, Ewa, Mentemeier, Sebastian
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Optimization and Control Probability Statistics Theory 60J05, 90C15, 60B20
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Stochastic Gradient Descent Revisited
par: Louzi, Azar
Publié: (2024)

Hidden regular variation for stochastic recursions with diagonal matrices
par: Damek, Ewa, et autres
Publié: (2025)

High-dimensional learning dynamics of multi-pass Stochastic Gradient Descent in multi-index models
par: Fan, Zhou, et autres
Publié: (2026)

Mini-Batch Covariance, Diffusion Limits, and Oracle Complexity in Stochastic Gradient Descent: A Sampling-Design Perspective
par: Zantedeschi, Daniel, et autres
Publié: (2026)

Stochastic Modified Flows for Riemannian Stochastic Gradient Descent
par: Gess, Benjamin, et autres
Publié: (2024)

Metric Entropy-Free Sample Complexity Bounds for Sample Average Approximation in Convex Stochastic Programming
par: Liu, Hongcheng, et autres
Publié: (2024)

On Strategic Measures and Optimality Properties in Discrete-Time Stochastic Control with Universally Measurable Policies
par: Yu, Huizhen
Publié: (2022)

Zero-one Laws for a Control Problem with Random Action Sets
par: Flesch, János, et autres
Publié: (2024)

Blackwell optimality and policy stability for long-run risk sensitive stochastic control
par: Bäuerle, Nicole, et autres
Publié: (2024)

Policy stability and ultimate stationarity in discounted risk-sensitive stochastic control
par: Bäuerle, Nicole, et autres
Publié: (2026)

Continuous-time mean field Markov decision models
par: Bäuerle, Nicole, et autres
Publié: (2023)

Stochastic dynamic programming with non-linear discounting
par: Bäuerle, Nicole, et autres
Publié: (2020)

Sample Average Approximation for Stochastic Programming with Equality Constraints
par: Lew, Thomas, et autres
Publié: (2022)

An Exponential Averaging Process with Strong Convergence Properties
par: Köhne, Frederik, et autres
Publié: (2025)

Large Deviation Asymptotics for the Supermarket Model with Growing Choices
par: Budhiraja, Amarjit, et autres
Publié: (2025)

The extremal position of a branching random walk on the general linear group
par: Grama, Ion, et autres
Publié: (2022)

Cutoff for Rewiring Dynamics on Perfect Matchings
par: Olesker-Taylor, Sam
Publié: (2021)

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent
par: Sheshukova, Marina, et autres
Publié: (2025)

Stochastic Control Problems Motivated by Sailboat Trajectory Optimization
par: Ciccarella, Carlo, et autres
Publié: (2024)

Constructive approaches to concentration inequalities with independent random variables
par: Moucer, Celine, et autres
Publié: (2024)

A Note on the Bias and Kemeny's Constant in Markov Reward Processes with an Application to Markov Chain Perturbation
par: Ortner, Ronald
Publié: (2024)

Properties of Turnpike Functions for Discounted Finite MDPs
par: Feinberg, Eugene A., et autres
Publié: (2025)

Dynamic programming for the stochastic matching model on general graphs: the case of the `N-graph'
par: Jean, Loïc, et autres
Publié: (2024)

Mean-Field Langevin Diffusions with Density-dependent Temperature
par: Huang, Yu-Jui, et autres
Publié: (2025)

Superpositions for General Conditional Mckean-Vlasov Stochastic Differential Equations
par: Feng, Qi, et autres
Publié: (2025)

A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization
par: Ruszczyński, Andrzej, et autres
Publié: (2024)

Probabilistic Zero Forcing with Vertex Reversion
par: Brennan, Zachary
Publié: (2024)

Fractional Backward Stochastic Partial Differential Equations with Applications to Stochastic Optimal Control of Partially Observed Systems driven by Lévy Processes
par: Ye, Yuyang, et autres
Publié: (2024)

Gaussian Approximation for Two-Timescale Linear Stochastic Approximation
par: Butyrin, Bogdan, et autres
Publié: (2025)

Many-Server Asymptotics for Join-the-Shortest-Queue: Large Deviations and Rare Events
par: Budhiraja, Amarjit, et autres
Publié: (2019)

Freidlin-Wentzell solutions of discrete Hamilton Jacobi equations
par: Aleandri, Michele, et autres
Publié: (2025)

A Graph Random Walk Method for Calculating Time-of-Flight Charge Mobility in Organic Semiconductors from Multiscale Simulations
par: Chen, Zhongquan, et autres
Publié: (2024)

Causal Hamilton-Jacobi-Bellman Equations for Anticipative Stochastic Optimal Control
par: Bank, Peter, et autres
Publié: (2025)

A probabilistic study of the set of stationary solutions to spatial kinetic-type equations
par: Mentemeier, Sebastian, et autres
Publié: (2025)

Optimal Asymptotic Rates for (Stochastic) Gradient Descent under the Local PL-Condition: A Geometric Approach
par: Kassing, Sebastian, et autres
Publié: (2026)

Robust Ergodic Control of Jump-Diffusion Systems under Drift and Intensity Uncertainty
par: Azze, Abel, et autres
Publié: (2026)

StochasticDominance.jl: A Julia Package for Higher Order Stochastic Dominance
par: Lakshmanan, Rajmadan, et autres
Publié: (2025)

Empirical Evaluation of Policy-Based Reinforcement Learning for Dynamic Service Control in an M/M/1 Queue
par: Walton, Joseph, et autres
Publié: (2026)

Asymptotic behavior of the extremal position in a multi-type branching random walk with heavy-tailed displacements
par: Kowalski, Krzysztof
Publié: (2025)

Computable Bounds on Convergence of Markov Chains in Wasserstein Distance via Contractive Drift
par: Qu, Yanlin, et autres
Publié: (2023)