Results 241 to 250 of about 1,380,157 (288)
Some of the next articles are maybe not open access.
1978
In Section 7.1, rate of convergence is defined, and our approach to the rate problem discussed. The rates are developed (in Section 7.3) for three separate cases, two forms of the basic KW procedure and the basic RM procedure. These algorithms are discussed in Section 7.1 and are put into a form which will be useful in the subsequent development.
Harold J. Kushner, Dean S. Clark
openaire +1 more source
In Section 7.1, rate of convergence is defined, and our approach to the rate problem discussed. The rates are developed (in Section 7.3) for three separate cases, two forms of the basic KW procedure and the basic RM procedure. These algorithms are discussed in Section 7.1 and are put into a form which will be useful in the subsequent development.
Harold J. Kushner, Dean S. Clark
openaire +1 more source
1997
The traditional definition of rate of convergence refers to the asymptotic properties of normalized errors about the limit point \( \bar \theta \). If e n = e for the Robbins—Monro algorithm, it is concerned with the asymptotic properties of \( U_n^ \in = \left( {\theta _n^ \in - \bar \theta } \right)/\sqrt \in \) for large n and small ∈.
Harold J. Kushner, G. George Yin
openaire +1 more source
The traditional definition of rate of convergence refers to the asymptotic properties of normalized errors about the limit point \( \bar \theta \). If e n = e for the Robbins—Monro algorithm, it is concerned with the asymptotic properties of \( U_n^ \in = \left( {\theta _n^ \in - \bar \theta } \right)/\sqrt \in \) for large n and small ∈.
Harold J. Kushner, G. George Yin
openaire +1 more source
2015
In this chapter, we study the local rate of convergence of r n (x) to r(x). We obtain full information on the first asymptotic term of r n (x) − r(x), and are rewarded with (i) a central limit theorem for r n (x) − r(x), and (ii) a way of helping the user decide how to choose the weights v ni of the estimate.
Gérard Biau, Luc Devroye
openaire +1 more source
In this chapter, we study the local rate of convergence of r n (x) to r(x). We obtain full information on the first asymptotic term of r n (x) − r(x), and are rewarded with (i) a central limit theorem for r n (x) − r(x), and (ii) a way of helping the user decide how to choose the weights v ni of the estimate.
Gérard Biau, Luc Devroye
openaire +1 more source
1996
This chapter gives some results on rates of convergence of M-estimators, including maximum likelihood estimators and least-squares estimators. We first state an abstract result, which is a generalization of the theorem on rates of convergence in Chapter 3.2, and next discuss some methods to establish the maximal inequalities needed for the application ...
Aad W. van der Vaart, Jon A. Wellner
openaire +1 more source
This chapter gives some results on rates of convergence of M-estimators, including maximum likelihood estimators and least-squares estimators. We first state an abstract result, which is a generalization of the theorem on rates of convergence in Chapter 3.2, and next discuss some methods to establish the maximal inequalities needed for the application ...
Aad W. van der Vaart, Jon A. Wellner
openaire +1 more source
Convergence Rates of SNP Density Estimators
Econometrica, 1996The seminonparametric (SNP) density estimator, proposed by \textit{A. R. Gallant} and \textit{D. W. Nychka} [ibid. 55, 363-390 (1987; Zbl 0631.62110)], has been used for structural, reduced form, and efficient method of moments estimation in economics, finance, and the health sciences.
Fenton, Victor M, Gallant, A Ronald
openaire +2 more sources
2018
In Chapter 3 we establish the \({O}(\sqrt{\varepsilon})\) error estimates for some two-scale expansions in H1 and the \({O}({\varepsilon})\) convergence rate for solutions \({u}_{\varepsilon}\) in L2. The results are obtained without any smoothness assumption on the coefficient matrix A. In this chapter we return to the problem of convergence rates and
openaire +1 more source
In Chapter 3 we establish the \({O}(\sqrt{\varepsilon})\) error estimates for some two-scale expansions in H1 and the \({O}({\varepsilon})\) convergence rate for solutions \({u}_{\varepsilon}\) in L2. The results are obtained without any smoothness assumption on the coefficient matrix A. In this chapter we return to the problem of convergence rates and
openaire +1 more source
Noisy optimization convergence rates
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation, 2013We consider noisy optimization problems, without the assumption of variance vanishing in the neighborhood of the optimum. We show mathematically that evolutionary algorithms with simple rules with exponential number of resamplings lead to a log-log convergence rate (log of the distance to the optimum linear in the log of the number of resamplings), as ...
Astete Morales, Sandra +2 more
openaire +1 more source
Is convergence rate monotonic?
Acta Oeconomica, 2007The paper aims to develop a model of nonlinear economic growth — with simple assumptions — which explains both Japan’s S -shape convergence path and the UK’s declining path toward the US between 1870–2000, and the development of other countries, as well as post-war reconstruction. According to the model, progress in stock of knowledge is formed by a
Csillik, P., Tarján, T.
openaire +2 more sources
1996
In this chapter we consider the general pattern recognition problem: Given the observation X and the training data D n = ((X 1, Y 1),..., (X n , Y n )) of independent identically distributed random variable pairs, we estimate the label Y by the decision . The error probability is .
Luc Devroye +2 more
openaire +1 more source
In this chapter we consider the general pattern recognition problem: Given the observation X and the training data D n = ((X 1, Y 1),..., (X n , Y n )) of independent identically distributed random variable pairs, we estimate the label Y by the decision . The error probability is .
Luc Devroye +2 more
openaire +1 more source
Subgeometric Rates of Convergence
2018We have seen in Chapter 11 that a recurrent irreducible kernel P on \(\mathsf {X}\times \mathscr {X}\) admits a unique invariant measure that is a probability measure \(\pi \) if the kernel is positive. If the kernel is, moreover, aperiodic, then the iterates of the kernel \(P^n(x,\cdot )\) converge to \(\pi \) in f-norm for \(\pi \)-almost all \(x\in \
Randal Douc +3 more
openaire +1 more source