Moriconi, R; Deisenroth, MP; Sesh Kumar, KS; (2020) High-dimensional Bayesian optimization using low-dimensional feature spaces. Machine Learning , 109 pp. 1925-1943. 10.1007/s10994-020-05899-z.

Preview

Text Deisenroth_High-dimensional Bayesian optimization using low-dimensional feature spaces_VoR.pdf - Published Version Download (4MB) | Preview

Abstract

Bayesian optimization (BO) is a powerful approach for seeking the global optimum of expensive black-box functions and has proven successful for fine tuning hyper-parameters of machine learning models. However, BO is practically limited to optimizing 10–20 parameters. To scale BO to high dimensions, we usually make structural assumptions on the decomposition of the objective and/or exploit the intrinsic lower dimensionality of the problem, e.g. by using linear projections. We could achieve a higher compression rate with nonlinear projections, but learning these nonlinear embeddings typically requires much data. This contradicts the BO objective of a relatively small evaluation budget. To address this challenge, we propose to learn a low-dimensional feature space jointly with (a) the response surface and (b) a reconstruction mapping. Our approach allows for optimization of BO’s acquisition function in the lower-dimensional subspace, which significantly simplifies the optimization problem. We reconstruct the original parameter space from the lower-dimensional subspace for evaluating the black-box function. For meaningful exploration, we solve a constrained optimization problem.

Downloads since deposit

Loading...

52Downloads

Download activity - last month

Export as JSONCSVXML

Loading...

Download activity - last 12 months

Export as JSONXMLCSV

Loading...

Downloads by country - last 12 months

Export as JSONCSVXML

Loading...

Archive Staff Only

View Item