We present a new class of perceptron-like algorithms with margin in which the "effective" learning rate, defined as the ratio of the learning rate to the length of the we...
The reduced basis method was introduced for the accurate online evaluation of solutions to a parameter dependent family of elliptic partial differential equations. ly, it can be ...
Peter Binev, Albert Cohen, Wolfgang Dahmen, Ronald...
The asymptotic convergence of parameterized variants of Newton's method for the solution of nonlinear systems of equations is considered. The original system is perturbed by a...
Nicholas I. M. Gould, Dominique Orban, Annick Sart...
The paper addresses the convergence of a decentralized Robbins-Monro algorithm for networks of agents. This algorithm combines local stochastic approximation steps for finding th...
We consider iterative algorithms of the form z := f(z), executed by a parallel or distributed computing system. We focus on asynchronous implementations whereby each processor ite...