On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions

DOI10.1007/s10589-022-00442-3OpenAlexW4313291849MaRDI QIDQ2696929

Claire Boyer, Antoine Godichon-Baggioni

Publication date: 17 April 2023

Published in: Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.09706

zbMATH Keywords

stochastic optimizationonline learningNewton algorithmaveraged stochastic algorithm

Mathematics Subject Classification ID

Mathematical programming (90Cxx)

Related Items (1)

Recursive ridge regression using second-order stochastic algorithms

Uses Software

• AdaGrad
• ADADELTA

Cites Work

• Unnamed Item
• A Stochastic Quasi-Newton Method for Large-Scale Optimization
• On the almost sure asymptotic behaviour of stochastic algorithm
• Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
• A Generalization of the Averaging Procedure: The Use of Two-Time-Scale Algorithms
• Acceleration of Stochastic Approximation by Averaging
• Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
• Optimization Methods for Large-Scale Machine Learning
• An Efficient Stochastic Newton Algorithm for Parameter Estimation in Logistic Regressions
• L^p and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective

This page was built for publication: On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions