Asymptotic Properties of Two Time-Scale Stochastic Approximation Algorithms with Constant Step Sizes

نویسندگان

  • Vladislav B. Tadić
  • Sean P. Meyn
چکیده

Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes are analyzed in this paper. The analysis is carried out for the algorithms with additive noise, as well as for the algorithms with non-additive noise. The algorithms with additive noise are considered for the case where the noise is state-dependent and admits the decomposition as a sum of a martingale difference sequence and a telescoping sequence. The algorithms with non-additive noise are analyzed for the case where the noise satisfies uniform or strong mixing conditions, as well as for the case where the noise is a Markov chain controlled by the algorithm states. Acknowledgement This paper is based upon work supported by the National Science Foundation under Award No. DMI 00 85165. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the National Science Foundation.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Iterate-averaging sign algorithms for adaptive filtering with applications to blind multiuser detection

Motivated by the recent developments on iterate averaging of recursive stochastic approximation algorithms and asymptotic analysis of sign-error algorithms for adaptive filtering, this work develops two-stage sign algorithms for adaptive filtering. The proposed algorithms are based on constructions of a sequence of estimates using large step sizes followed by iterate averaging. Our main effort ...

متن کامل

Constant Step Size Least-Mean-Square: Bias-Variance Trade-offs and Optimal Sampling Distributions

We consider the least-squares regression problem and provide a detailed asymptotic analysis of the performance of averaged constant-step-size stochastic gradient descent (a.k.a. least-mean-squares). In the strongly-convex case, we provide an asymptotic expansion up to explicit exponentially decaying terms. Our analysis leads to new insights into stochastic approximation algorithms: (a) it gives...

متن کامل

Regime Switching Stochastic Approximation Algorithms with Application to Adaptive Discrete Stochastic Optimization

This work is devoted to a class of stochastic approximation problems with regime switching modulated by a discrete-time Markov chain. Our motivation stems from using stochastic recursive algorithms for tracking Markovian parameters such as those in spreading code optimization in CDMA (code division multiple access) wireless communication. The algorithm uses constant step size to update the incr...

متن کامل

Convergence Rate and Averaging of Nonlinear Two - Time - Scale Stochastic Approximation Algorithms

The first aim of this paper is to establish the weak convergence rate of nonlinear two-time-scale stochastic approximation algorithms. Its second aim is to introduce the averaging principle in the context of two-time-scale stochastic approximation algorithms. We first define the notion of asymptotic efficiency in this framework, then introduce the averaged two-time-scale stochastic approximatio...

متن کامل

Averaged Least-Mean-Squares: Bias-Variance Trade-offs and Optimal Sampling Distributions

We consider the least-squares regression problem and provide a detailed asymptotic analysis of the performance of averaged constant-step-size stochastic gradient descent. In the strongly-convex case, we provide an asymptotic expansion up to explicit exponentially decaying terms. Our analysis leads to new insights into stochastic approximation algorithms: (a) it gives a tighter bound on the allo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007