A Novel Adaptive Algorithm with Optimum Rates of Convergence

Sally S. L. Shao; Percy P. C. Yip

A Novel Adaptive Algorithm with Optimum Rates of Convergence

AI WARE, Inc

Research output: Contribution to journal › Article › peer-review

Abstract

We propose a new adaptive algorithm with decreasing step-size for stochastic approximations. The use of adaptive algorithm is widely spread in various applications across the fields such as system identification and adaptive control. We analyze the rate of convergence of the proposed algorithms. An averaging algorithm, on its optimality of the rate of convergence, is using to control the step sizes. Our proofs are based on recent results in stochastic approximations and Guass approximation Theorem.

Original language	American English
Journal	3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings
State	Published - Jan 1 2000

Disciplines

Mathematics

Access to Document

http://paws.kettering.edu/~ktebeest/2000/shao.html

Cite this

@article{f4a89f51f32a42f0953785bae7d444e1,

title = "A Novel Adaptive Algorithm with Optimum Rates of Convergence",

abstract = " We propose a new adaptive algorithm with decreasing step-size for stochastic approximations. The use of adaptive algorithm is widely spread in various applications across the fields such as system identification and adaptive control. We analyze the rate of convergence of the proposed algorithms. An averaging algorithm, on its optimality of the rate of convergence, is using to control the step sizes. Our proofs are based on recent results in stochastic approximations and Guass approximation Theorem.",

author = "Shao, \{Sally S. L.\} and Yip, \{Percy P. C.\}",

note = "S. Shao and P. P. C. Yip. (2000) A novel adaptive algorithm with optimum rates of convergence. 3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings, 1-20.",

year = "2000",

month = jan,

day = "1",

language = "American English",

journal = "3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings",

}

TY - JOUR

T1 - A Novel Adaptive Algorithm with Optimum Rates of Convergence

AU - Shao, Sally S. L.

AU - Yip, Percy P. C.

N1 - S. Shao and P. P. C. Yip. (2000) A novel adaptive algorithm with optimum rates of convergence. 3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings, 1-20.

PY - 2000/1/1

Y1 - 2000/1/1

N2 - We propose a new adaptive algorithm with decreasing step-size for stochastic approximations. The use of adaptive algorithm is widely spread in various applications across the fields such as system identification and adaptive control. We analyze the rate of convergence of the proposed algorithms. An averaging algorithm, on its optimality of the rate of convergence, is using to control the step sizes. Our proofs are based on recent results in stochastic approximations and Guass approximation Theorem.

AB - We propose a new adaptive algorithm with decreasing step-size for stochastic approximations. The use of adaptive algorithm is widely spread in various applications across the fields such as system identification and adaptive control. We analyze the rate of convergence of the proposed algorithms. An averaging algorithm, on its optimality of the rate of convergence, is using to control the step sizes. Our proofs are based on recent results in stochastic approximations and Guass approximation Theorem.

UR - https://engagedscholarship.csuohio.edu/scimath_facpub/50

UR - http://paws.kettering.edu/~ktebeest/2000/shao.html

M3 - Article

JO - 3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings

JF - 3rd Forum on Numerics and Modeling for Partial Differential Equations, NUMPEDS 2000 proceedings

ER -

A Novel Adaptive Algorithm with Optimum Rates of Convergence

Abstract

Disciplines

Access to Document

Other files and links

Cite this