Asymptotic Properties of Some Projection-based Robbins-Monro Procedures in a Hilbert Space
نویسندگان
چکیده
Let H be an infinite-dimensional real separable Hilbert space. Given an unknown mapping M :H (r)H that can only be observed with noise, we consider two modified Robbins-Monro procedures to estimate the zero point ?o ( H of M. These procedures work in appropriate finite dimensional sub-spaces of growing dimension. Almost-sure convergence, functional central limit theorem (hence asymptotic normality), law of iterated logarithm (hence almost-sure loglog rate of convergence), and mean rate of convergence are obtained for Hilbert spacevalued mixingale, (-dependent error processes.
منابع مشابه
Efficient Robbins-Monro Procedure for Binary Data
The Robbins-Monro procedure does not perform well in the estimation of extreme quantiles, because the procedure is implemented using asymptotic results, which are not suitable for binary data. Here we propose a modification of the Robbins-Monro procedure and derive the optimal procedure for binary data under some reasonable approximations. The improvement obtained by using the optimal procedure...
متن کاملStochastic Approximation: A Survey
Stochastic recursive algorithms, also known as stochastic approximation, take many forms and have numerous applications. It is the asymptotic properties that are of interest. The early history, starting with the work of Robbins and Monro, is discussed. An approach to proofs of convergence with probability one is illustrated by a stability-type argument. For general noise processes and algorithm...
متن کاملSOME PROPERTIES OF FUZZY HILBERT SPACES AND NORM OF OPERATORS
In the present paper we define the notion of fuzzy inner productand study the properties of the corresponding fuzzy norm. In particular, it isshown that the Cauchy-Schwarz inequality holds. Moreover, it is proved thatevery such fuzzy inner product space can be imbedded in a complete one andthat every subspace of a fuzzy Hilbert space has a complementary subspace.Finally, the notions of fuzzy bo...
متن کاملNon-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning
In this paper, we consider the minimization of a convex objective function defined on a Hilbert space, which is only available through unbiased estimates of its gradients. This problem includes standard machine learning algorithms such as kernel logistic regression and least-squares regression, and is commonly referred to as a stochastic approximation problem in the operations research communit...
متن کاملSome Properties of Continuous $K$-frames in Hilbert Spaces
The theory of continuous frames in Hilbert spaces is extended, by using the concepts of measure spaces, in order to get the results of a new application of operator theory. The $K$-frames were introduced by G$breve{mbox{a}}$vruta (2012) for Hilbert spaces to study atomic systems with respect to a bounded linear operator. Due to the structure of $K$-frames, there are many differences between...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1992