DoE2Vec: Deep-learning Based Features for Exploratory Landscape Analysis

Abstract

We propose DoE2Vec, a variational autoencoder (VAE)-based methodology to learn optimization landscape characteristics for downstream meta-learning tasks, e.g., automated selection of optimization algorithms. Principally, using large training data sets generated with a random function generator, DoE2Vec self-learns an informative latent representation for any design of experiments (DoE). Unlike the classical exploratory landscape analysis (ELA) method, our approach does not require any feature engineering and is easily applicable to high-dimensional search spaces. For validation, the proposed approach is used for three downstream classification tasks. We show that the latent representations can significantly boost performances when being used complementary to the classical ELA features.