Convergence Rates and Decoupling in Linear Stochastic Approximation Algorithms

DOI10.1137/14095707XzbMath1328.60085arXiv1501.02414MaRDI QIDQ5254881

Michael A. Kouritzin, Samira Sadeghi

Publication date: 10 June 2015

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1501.02414

zbMATH Keywords

stochastic approximationrandom matriceslinear processheavy tailslong-range dependenceMarcinkiewicz strong law of large numbersalmost sure convergence rates

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Random matrices (probabilistic aspects) (60B20) Strong limit theorems (60F15) Stochastic approximation (62L20) Rate of convergence, degree of approximation (41A25)

Related Items (3)

On almost sure limit theorems for heavy-tailed products of long-range dependent linear processes ⋮ EXPLICIT HESTON SOLUTIONS AND STOCHASTIC APPROXIMATION FOR PATH-DEPENDENT OPTION PRICING ⋮ A Marcinkiewicz-Zygmund type strong law for weighted sums of \(\phi \)-mixing random variables and its applications

Uses Software

• plfit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming
• Convergence rates in the strong law for bounded mixing sequences
• On the interrelation of almost sure invariance principles for certain stochastic adaptive algorithms and for partial sums of random variables
• An almost sure invariance principle for stochastic approximation procedures in linear filtering theory
• Convergence of the Robbins-Monro method for linear problems in a Banach space
• A maximal inequality and dependent Marcinkiewicz-Zygmund strong laws
• The averaged Robbins-Monro method for linear problems in a Banach space
• State Observers with Random Sampling Times and Convergence Analysis of Double-Indexed and Randomly Weighted Sums of Mixing Processes
• Convergence of an adaptive linear estimation algorithm
• On the Almost Sure Rate of Convergence of Linear Stochastic Approximation Algorithms
• Power-Law Distributions in Empirical Data
• Stochastic approximation from ergodic sample for linear regression
• Stochastic approximation with correlated data
• On almost-sure bounds for the LMS algorithm
• Noise conditions for prespecified convergence rates of stochastic approximation algorithms
• Inductive methods and rates of R^th-mean convergence in adaptive filtering
• On the convergence of linear stochastic approximation procedures
• Marcinkiewicz law of large numbers for outer products of heavy-tailed, long-range dependent data
• A Stochastic Approximation Method
• Marcinkiewicz-Zygmund strong laws for infinite variance time series.

This page was built for publication: Convergence Rates and Decoupling in Linear Stochastic Approximation Algorithms