Learning to Guide Random Search
From MaRDI portal
Publication:6339426
arXiv2004.12214MaRDI QIDQ6339426
Author name not available (Why is that?)
Publication date: 25 April 2020
Abstract: We are interested in derivative-free optimization of high-dimensional functions. The sample complexity of existing methods is high and depends on problem dimensionality, unlike the dimensionality-independent rates of first-order methods. The recent success of deep learning suggests that many datasets lie on low-dimensional manifolds that can be represented by deep nonlinear models. We therefore consider derivative-free optimization of a high-dimensional function that lies on a latent low-dimensional manifold. We develop an online learning approach that learns this manifold while performing the optimization. In other words, we jointly learn the manifold and optimize the function. Our analysis suggests that the presented method significantly reduces sample complexity. We empirically evaluate the method on continuous optimization benchmarks and high-dimensional continuous control problems. Our method achieves significantly lower sample complexity than Augmented Random Search, Bayesian optimization, covariance matrix adaptation (CMA-ES), and other derivative-free optimization algorithms.
Has companion code repository: https://github.com/intel-isl/LMRS
This page was built for publication: Learning to Guide Random Search
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6339426)
