Recomi (REpeated COrrelation Matrix Inversion) is a polynomially fast algorithm for searching optimally stable solutions of the perceptron learning problem. For random unbiased and biased patterns it is shown that the algorithm is able to find optimal solutions, if any exist, in at worst O(N^4) floating point operations. Even beyond the critical storage capacity alpha_c the algorithm is able to find locally stable solutions (with negative stability) at the same speed. There are no divergent time scales in the learning process. A full proof of convergence cannot yet be given, only major constituents of a proof are shown.
@article{arxiv.cond-mat/9407116,
title = {A polynomial training algorithm for calculating perceptrons of optimal stability},
author = {Jorg Imhoff},
journal= {arXiv preprint arXiv:cond-mat/9407116},
year = {2009}
}