Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
Papenmeier, Leonard; Nardi, Luigi; Poloczek, Matthias
Abstract
Impactful applications such as materials discovery, hardware design, neural architecture search, or portfolio optimization require optimizing high-dimensional black-box functions with mixed and combinatorial input spaces. While Bayesian optimization has recently made significant progress in solving such problems, an in-depth analysis reveals that the current state-of-the-art methods are not reliable. Their performances degrade substantially when the unknown optima of the function do not have a certain structure. To fill the need for a reliable algorithm for combinatorial and mixed spaces, this paper proposes Bounce that relies on a novel map of various variable types into nested embeddings of increasing dimensionality. Comprehensive experiments show that Bounce reliably achieves and often even improves upon state-of-the-art performance on a variety of high-dimensional problems.
Keywords
Bayesian Optimization
Cite as
Papenmeier, L., Nardi, L., & Poloczek, M. (2023). Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces. In Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., & Levine, S. (Eds.),
Advances in Neural Information Processing Systems (-, pp. 1764–1793). Advances in Neural Information Processing Systems: Vol. 36. Red Hook, NY, United States: Curran Associates.
Details
Publication type
Research article in proceedings (conference)
Peer reviewed
Yes
Publication status
Published
Year
2023
Conference
37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Venue
New Orleans Ernest N. Morial Convention Center
Volume
36
Book title
Advances in Neural Information Processing Systems
Editor
Oh, A.; Naumann, T.; Globerson, A.; Saenko, K.; Hardt, M.; Levine, S.
Start page
1764
End page
1793
Edition
-
Volume
36
Title of series
Advances in Neural Information Processing Systems
Publisher
Curran Associates
Place
Red Hook, NY, United States
Language
English
ISSN
1049-5258
ISBN
9781713899921
Full text
