Convergence of a Distributed Kiefer-Wolfowitz Algorithm
نویسندگان
چکیده
This paper proposes a proof of the convergence distributed and asynchronous version Kiefer-Wolfowitz algorithm where agents do not exchange information with one another.
منابع مشابه
A Kiefer-Wolfowitz algorithm with randomized differences
A Kiefer–Wolfowitz or simultaneous perturbation algorithm that uses either one-sided or two-sided randomized differences and truncations at randomly varying bounds is given in this paper. At each iteration of the algorithm only two observations are required in contrast to 2` observations, where ` is the dimension, in the classical algorithm. The algorithm given here is shown to be convergent un...
متن کاملA companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm
A stochastic algorithm for the recursive approximation of the location θ of a maximum of a regression function has been introduced by Kiefer and Wolfowitz (1952) in the univariate framework, and by Blum (1954) in the multivariate case. The aim of this paper is to provide a companion algorithm to the Kiefer-Wolfowitz-Blum algorithm, which allows to simultaneously recursively approximate the size...
متن کاملA Kiefer - Wolfowitz Theorem for Convex Densities
Kiefer and Wolfowitz [14] showed that if F is a strictly curved concave distribution function (corresponding to a strictly monotone density f), then the Maximum Likelihood Estimator F̂n, which is, in fact, the least concave majorant of the empirical distribution function Fn, differs from the empirical distribution function in the uniform norm by no more than a constant times (n logn)2/3 almost s...
متن کاملKiefer Wolfowitz Algorithm is Asymptotically Optimal for a Class of Non-Stationary Bandit Problems
We consider the problem of designing an allocation rule or an “online learning algorithm” for a class of bandit problems in which the set of control actions available at each time t is a convex, compact subset of R. Upon choosing an action x at time t, the algorithm obtains a noisy value of the unknown and time-varying function ft evaluated at x. The “regret” of an algorithm is the gap between ...
متن کاملA Kiefer – Wolfowitz Comparison Theorem for Wicksell ’ S Problem
We extend the isotonic analysis for Wicksell's problem to estimate a regression function, which is motivated by the problem of estimating dark matter distribution in astronomy. The main result is a version of the Kiefer–Wolfowitz theorem comparing the empirical distribution to its least concave majorant, but with a convergence rate n −1 log n faster than n −2/3 log n. The main result is useful ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Stochastic systems
سال: 2021
ISSN: ['1946-5238']
DOI: https://doi.org/10.1287/stsy.2021.0080