Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization

Author name not available (Why is that?)

Publication date: 18 May 2017

Abstract: The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) is a popular method to deal with nonconvex and/or stochastic optimization problems when the gradient information is not available. Being based on the CMA-ES, the recently proposed Matrix Adaptation Evolution Strategy (MA-ES) provides a rather surprising result that the covariance matrix and all associated operations (e.g., potentially unstable eigendecomposition) can be replaced in the CMA-ES by a updated transformation matrix without any loss of performance. In order to further simplify MA-ES and reduce its

time and storage complexity to

, we present the Limited-Memory Matrix Adaptation Evolution Strategy (LM-MA-ES) for efficient zeroth order large-scale optimization. The algorithm demonstrates state-of-the-art performance on a set of established large-scale benchmarks. We explore the algorithm on the problem of generating adversarial inputs for a (non-smooth) random forest classifier, demonstrating a surprising vulnerability of the classifier.

Has companion code repository: https://github.com/luna97/matrix-adaptation-exploiting-gradient-evolution-strategy/blob/main/utility/es.py

This page was built for publication: Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6286844)