The Fundamental Learning Problem that Genetic Algorithms with Uniform Crossover Solve Efficiently and Repeatedly As Evolution Proceeds

TL;DR

This paper proves that genetic algorithms with uniform crossover can efficiently learn complex problems like noisy parity functions by leveraging implicit concurrency, providing near-optimal bounds on learning time and queries.

Contribution

It introduces the concept of implicit concurrency in genetic algorithms and demonstrates its effectiveness in efficiently solving noisy parity learning problems with rigorous bounds.

Findings

UGAs can learn noisy parity functions in O(log^1.585 n) queries

Implicit concurrency underpins efficient non-local optimization in UGAs

First rigorous proof of efficient learning in evolutionary algorithms on a complex problem

Abstract

This paper establishes theoretical bonafides for implicit concurrent multivariate effect evaluation--implicit concurrency for short---a broad and versatile computational learning efficiency thought to underlie general-purpose, non-local, noise-tolerant optimization in genetic algorithms with uniform crossover (UGAs). We demonstrate that implicit concurrency is indeed a form of efficient learning by showing that it can be used to obtain close-to-optimal bounds on the time and queries required to approximately correctly solve a constrained version (k=7, \eta=1/5) of a recognizable computational learning problem: learning parities with noisy membership queries. We argue that a UGA that treats the noisy membership query oracle as a fitness function can be straightforwardly used to approximately correctly learn the essential attributes in O(log^1.585 n) queries and O(n log^1.585 n) time, where n is the total number of attributes. Our proof relies on an accessible symmetry argument and the use of statistical hypothesis testing to reject a global null hypothesis at the 10^-100 level of significance. It is, to the best of our knowledge, the first relatively rigorous identification of efficient computational learning in an evolutionary algorithm on a non-trivial learning problem.