On adaptive stochastic optimization for streaming data: a Newton's method with O(dN) operations

MaRDI QIDQ6982645zbMATH OpenFDO

Authors Antoine Godichon-Baggioni

Publication date 16 May 2025

Published in Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://jmlr.org/papers/v26/23-1565.html

zbMATH Keywords

large-scaleonline learningsecond-order methodsstochastic gradient methodsstochastic optimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic programming (90C15)

Cites work

• L^p and almost sure rates of convergence of averaged stochastic gradient algorithms: locally strongly convex objective
• A generalization of the averaging procedure: the use of two-time-scale algorithms
• A Stochastic Approximation Method
• A stochastic Gauss–Newton algorithm for regularized semi-discrete optimal transport
• Acceleration of Stochastic Approximation by Averaging
• Adaptive subgradient methods for online learning and stochastic optimization
• Adjustment of an Inverse Matrix Corresponding to a Change in One Element of a Given Matrix
• An efficient stochastic Newton algorithm for parameter estimation in logistic regressions
• Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
• Asymptotic and finite-sample properties of estimators based on stochastic gradients
• scientific article; zbMATH DE number 48727 (Why is no real title available?)
• scientific article; zbMATH DE number 1972910 (Why is no real title available?)
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Non-asymptotic analysis of Stochastic approximation algorithms for streaming data
• Numerical Optimization
• On Asymptotic Normality in Stochastic Approximation
• On the almost sure asymptotic behaviour of stochastic algorithm
• On the asymptotic rate of convergence of stochastic Newton algorithms and their weighted averaged versions
• On the inversion-free Newton's method and its applications
• Online estimation of the asymptotic variance for averaged stochastic gradient algorithms
• Online stochastic Newton methods for estimating the geometric median and applications
• Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm
• Optimization methods for large-scale machine learning
• Recursive ridge regression using second-order stochastic algorithms
• Reinforcement learning. An introduction
• Robust Stochastic Approximation Approach to Stochastic Programming
• Stochastic quasi-gradient methods: variance reduction via Jacobian sketching

Cited in

(1)

• Complexity reduction in online stochastic Newton methods with potential \(\mathcal{O}(Nd)\) total cost

This page was built for publication: On adaptive stochastic optimization for streaming data: a Newton's method with \( \mathcal{O}(dN)\) operations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6982645)