On the choice of the low-dimensional domain for high-dimensional bayesian optimization using random embeddings

Binois, Mickaël; Ginsbourger, David; Roustant, Olivier (2020). On the choice of the low-dimensional domain for high-dimensional bayesian optimization using random embeddings. Journal of global optimization, 76(1), pp. 69-90. Springer 10.1007/s10898-019-00839-1

[img] Text
Binois2020_Article_OnTheChoiceOfTheLow-dimensiona.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

The challenge of taking many variables into account in optimization problems may be overcome under the hypothesis of low effective dimensionality. Then, the search of solutions can be reduced to the random embedding of a low dimensional space into the original one, resulting in a more manageable optimization problem. Specifically, in the case of time consuming black-box functions and when the budget of evaluations is severely limited, global optimization with random embeddings appears as a sound alternative to random search. Yet, in the case of box constraints on the native variables, defining suitable bounds on a low dimensional domain appears to be complex. Indeed, a small search domain does not guarantee to find a solution even under restrictive hypotheses about the function, while a larger one may slow down convergence dramatically. Here we tackle the issue of low-dimensional domain selection based on a detailed study of the properties of the random embedding, giving insight on the aforementioned difficulties. In particular, we describe a minimal low-dimensional set in correspondence with the embedded search space. We additionally show that an alternative equivalent embedding procedure yields simultaneously a simpler definition of the low-dimensional minimal set and better properties in practice. Finally, the performance and robustness gains of the proposed enhancements for Bayesian optimization are illustrated on numerical examples.

Item Type:

Journal Article (Original Article)


08 Faculty of Science > Department of Mathematics and Statistics > Institute of Mathematical Statistics and Actuarial Science

UniBE Contributor:

Ginsbourger, David


500 Science > 510 Mathematics








David Ginsbourger

Date Deposited:

14 Jan 2020 09:08

Last Modified:

14 Jan 2020 09:08

Publisher DOI:






Actions (login required)

Edit item Edit item
Provide Feedback