Good practices for Bayesian optimization of high dimensional structured spaces

Eero Siivola, Andrei Paleyes, Javier González, Aki Vehtari

Research output: Contribution to journalLetterScientificpeer-review

Abstract

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.
Original languageEnglish
Number of pages13
JournalApplied AI Letters
DOIs
Publication statusPublished - 2021
MoE publication typeA1 Journal article-refereed

Fingerprint

Dive into the research topics of 'Good practices for Bayesian optimization of high dimensional structured spaces'. Together they form a unique fingerprint.

Cite this