Bounce : Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
(2023) 37th Conference on Neural Information Processing Systems, NeurIPS 2023 In Advances in Neural Information Processing Systems 36.- 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... (More)
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.
(Less)
- author
- Papenmeier, Leonard LU ; Nardi, Luigi LU and Poloczek, Matthias
- organization
- publishing date
- 2023
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Advances in Neural Information Processing Systems
- series title
- Advances in Neural Information Processing Systems
- volume
- 36
- conference name
- 37th Conference on Neural Information Processing Systems, NeurIPS 2023
- conference location
- New Orleans, United States
- conference dates
- 2023-12-10 - 2023-12-16
- external identifiers
-
- scopus:85191172653
- ISSN
- 1049-5258
- language
- English
- LU publication?
- yes
- id
- b70b82d1-50df-438d-a139-f0ca64943280
- date added to LUP
- 2024-05-07 15:05:11
- date last changed
- 2024-05-07 15:06:36
@inproceedings{b70b82d1-50df-438d-a139-f0ca64943280, abstract = {{<p>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.</p>}}, author = {{Papenmeier, Leonard and Nardi, Luigi and Poloczek, Matthias}}, booktitle = {{Advances in Neural Information Processing Systems}}, issn = {{1049-5258}}, language = {{eng}}, series = {{Advances in Neural Information Processing Systems}}, title = {{Bounce : Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces}}, volume = {{36}}, year = {{2023}}, }