z-logo
open-access-imgOpen Access
Good practices for Bayesian optimization of high dimensional structured spaces
Author(s) -
Siivola Eero,
Paleyes Andrei,
González Javier,
Vehtari Aki
Publication year - 2021
Publication title -
applied ai letters
Language(s) - English
Resource type - Journals
ISSN - 2689-5595
DOI - 10.1002/ail2.24
Subject(s) - bayesian optimization , curse of dimensionality , computer science , space (punctuation) , high dimensional , bayesian probability , optimization problem , machine learning , function (biology) , function optimization , artificial intelligence , data science , data mining , algorithm , genetic algorithm , operating system , evolutionary biology , biology
The increasing availability of structured but high dimensional data has opened new opportunities for optimization. One emerging and promising avenue is the exploration of unsupervised methods for projecting structured high dimensional data into low dimensional continuous representations, simplifying the optimization problem and enabling the application of traditional optimization methods. However, this line of research has been purely methodological with little connection to the needs of practitioners so far. In this article, we study the effect of different search space design choices for performing Bayesian optimization in high dimensional structured datasets. In particular, we analyses the influence of the dimensionality of the latent space, the role of the acquisition function and evaluate new methods to automatically define the optimization bounds in the latent space. Finally, based on experimental results using synthetic and real datasets, we provide recommendations for the practitioners.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here