Expectation-maximization (EM) is an iterative algorithm for finding the maximum likelihood or maximum a posteriori estimate of the parameters of a statistical model with latent variables or when we have missing data. In this work, we view EM in a generalized surrogate optimization framework and analyze its convergence rate under commonly-used assumptions. We show a lower bound on the decrease i...

We pose the problem of determining the rate of convergence at which AdaBoost minimizes exponential loss. Boosting is the problem of combining many “weak,” high-error hypotheses to generate a single “strong” hypothesis with very low error. The AdaBoost algorithm of Freund and Schapire (1997) is shown in Figure 1. Here we are given m labeled training examples (x1, y1), . . . , (xm, ym) where the ...

The wavelet transform-domain least-mean square (WTDLMS) algorithm uses the self-orthogonalizing technique to improve the convergence performance of LMS. In WTDLMS algorithm, the trade-off between the steady-state error and the convergence rate is obtained by the fixed step-size. In this paper, the WTDLMS adaptive algorithm with variable step-size (VSS) is established. The step-size in each subf...

The aim of this paper is to improve the convergence rate of frame algorithm based on Richardson iteration and Chebyshev methods. Based on Richardson iteration method, we first square the existing convergence rate of frame algorithm which in turn the number of iterations would be bisected and increased speed of convergence is achieved. Afterward, by using Chebyshev polynomials, we improve this s...

in this paper, a numerical solution for a system of linear fredholm integro-differential equations by means of the sinc method is considered. this approximation reduces the system of integro-differential equations to an explicit system of algebraic equations. the exponential convergence rate $o(e^{-k sqrt{n}})$ of the method is proved. the analytical results are illustrated with numerical examp...

least squares method (lsm) is an accurate and rapid method for solving some analytical andnumerical problems. this method can be used to estimate the average reservoir pressure in well testanalysis. in fact, it may be employed to estimate parameters such as permeability (k) and porevolume (vp). regarding this point, buildup, drawdown, late transient test data, modified muskatmethod, interferenc...

in this paper, we will present a modification of the preconditioned aor-type method for solving the linear system. a theorem is given to show the convergence rate of modification of the preconditioned aor methods that can be enlarged than the convergence aor method.

In this paper, a numerical solution for a system of linear Fredholm integro-differential equations by means of the sinc method is considered. This approximation reduces the system of integro-differential equations to an explicit system of algebraic equations. The exponential convergence rate $O(e^{-k sqrt{N}})$ of the method is proved. The analytical results are illustrated with numerical examp...