Linking the statistic and the machine learning literature, we provide new general results on the convergence of stochastic approximation schemes and inexact Newton methods. Building on these results, we put forward a new optimization scheme that we call generalized inexact Newton method (GINM)....

This study focuses on estimating reliability P[YX], where Y has a Zeghdoudi distribution with parameter a, X has a Zeghdoudi distribution with one outlier present and parameter c, and the remaining (n - 1) random variables are from a Zeghdoudi distribution with parameter b, in order for X and Y...

Linking the statistic and the machine learning literature, we provide new general results on the convergence of stochastic approximation schemes and inexact Newton methods. Building on these results, we put forward a new optimization scheme that we call generalized inexact Newton method (GINM)....