Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 17 of 79
Back to Result List

Scalable Hyperparameter Optimization with Lazy Gaussian Processes

  • Most machine learning methods require careful selection of hyper-parameters in order to train a high performing model with good generalization abilities. Hence, several automatic selection algorithms have been introduced to overcome tedious manual (try and error) tuning of these parameters. Due to its very high sample efficiency, Bayesian Optimization over a Gaussian Processes modeling of theMost machine learning methods require careful selection of hyper-parameters in order to train a high performing model with good generalization abilities. Hence, several automatic selection algorithms have been introduced to overcome tedious manual (try and error) tuning of these parameters. Due to its very high sample efficiency, Bayesian Optimization over a Gaussian Processes modeling of the parameter space has become the method of choice. Unfortunately, this approach suffers from a cubic compute complexity due to underlying Cholesky factorization, which makes it very hard to be scaled beyond a small number of sampling steps. In this paper, we present a novel, highly accurate approximation of the underlying Gaussian Process. Reducing its computational complexity from cubic to quadratic allows an efficient strong scaling of Bayesian Optimization while outperforming the previous approach regarding optimization accuracy. First experiments show speedups of a factor of 162 in single node and further speed up by a factor of 5 in a parallel environment.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar

Statistics

frontdoor_oas
Metadaten
Author:Raju Ram, Sabine Müller, Franz-Josef Pfreundt, Nicolas R Gauger, Janis KeuperORCiDGND
Creating Corporation:IEEE
Year of Publication:2019
ISBN:978-1-7281-5985-0 (Online)
ISBN:978-1-7281-5986-7 (Print on Demand)
Language:English
DDC classes:000 Allgemeines, Informatik, Informationswissenschaft
Parent Title (English):Proceedings of MLHPC 2019: 5th Workshop on Machine Learning in HPC Environments
First Page:56
Last Page:65
Document Type:Conference Proceeding
Institutes:Bibliografie
Open Access:Zugriffsbeschränkt
Release Date:2020/01/21
Licence (German):License LogoEs gilt das UrhG
Note:
2019 IEEE/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC), 18 Nov. 2019, Denver, Colorado, USA.
Held in conjunction with SC19:  The International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, Colorado, November 17-22, 2019
DOI:https://doi.org/10.1109/MLHPC49564.2019.00011