A view of Estimation of Distribution Algorithms through the lens of Expectation-Maximization

2019/05/24 by Brookes, David H., Busia, Akosua, Fannjiang, Clara +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1905.10474

Abstract

We show that a large class of Estimation of Distribution Algorithms, including, but not limited to, Covariance Matrix Adaption, can be written as a Monte Carlo Expectation-Maximization algorithm, and as exact EM in the limit of infinite samples. Because EM sits on a rigorous statistical foundation and has been thoroughly analyzed, this connection provides a new coherent framework with which to reason about EDAs.

Cited by

• Leveraging Discrete Function Decomposability for Scientific Design

Related

• EM algorithm and variants: an informal tutorial
• The expectation-maximization algorithm
• Theory of Estimation-of-Distribution Algorithms
• On the Convergence of the EM Algorithm: A Data-Adaptive Analysis
• Convergence of a stochastic approximation version of the EM algorithm