Finite dimensional approximation and Newton-based algorithm for stochastic approximation in Hilbert space

DOI10.1016/j.automatica.2009.09.031zbMath1192.90133OpenAlexW2052899080WikidataQ56565422 ScholiaQ56565422MaRDI QIDQ976221

Vivek S. Borkar, Ankur A. Kulkarni

Publication date: 17 June 2010

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2009.09.031

zbMATH Keywords

stochastic programmingconvex optimizationstochastic approximationHilbert spacesrandom projection

Mathematics Subject Classification ID

Stochastic programming (90C15) Programming in abstract spaces (90C48)

Related Items

Uncertainty Quantification for Stochastic Approximation Limits Using Chaos Expansion

Uses Software

• SUTIL

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Recourse-based stochastic nonlinear programming: properties and Benders-SQP algorithms
• An invariance principle for a finite dimensional stochastic approximation method in a Hilbert space
• Minimizing noisy functionals in Hilbert space: An extension of the Kiefer-Wolfowitz procedure
• Stochastic convex programming: Kuhn-Tucker conditions
• Martingales and the Robbins-Monro procedure in \(D[0,1\)]
• Nonparametric adaptive learning with feedback
• A simulation-based approach to two-stage stochastic programming with recourse
• The empirical behavior of sampling methods for stochastic programming
• A note on linear function approximation using random projections
• On the mathematical foundations of learning
• Linear Programming under Uncertainty
• Asymptotic Properties of Some Projection-based Robbins-Monro Procedures in a Hilbert Space
• Hitting-time and occupation-time bounds implied by drift analysis with applications
• An invariance principle for the Robbins-Monro process in a Hilbert space
• Numerical Optimization
• Introduction to Stochastic Programming
• Variable-sample methods for stochastic optimization
• Adaptive Newton-based multivariate smoothed functional algorithms for simulation optimization
• Fast Monte Carlo Algorithms for Matrices I: Approximating Matrix Multiplication
• $ℵ_0$-categoricity of linear orderings
• Equivalent Norms for Sobolev Spaces
• Stochastic Programs with Recourse
• On the Stochastic Approximation Method of Robbins and Monro
• Stochastic Estimation of the Maximum of a Regression Function
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one