Genetic Algorithms for Discovery of Matrix Multiplication Methods
András Joó, Anikó Ekárt, Juan Pablo Neirotti · IEEE Transactions on Evolutionary Computation · 2012
We present a parallel genetic algorithm for finding matrix multiplication algorithms. For 3 3 matrices our genetic algorithm successfully discovered algorithms requiring 23 multiplications, which are equivalent to the currently best known human-developed algorithms. We also studied cases with fewer multiplications and found an approximate solution for 22 multiplications.