Name
Abstract | ||
|---|---|---|
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to construct the parameter search space dynamically, (2) efficient implementation of both searching and pruning strategies, and (3) easy-to-setup, versatile architecture that can be deployed for various purposes, ranging from scalable distributed computing to light-weight experiment conducted via interactive interface. In order to prove our point, we will introduce Optuna, an optimization software which is a culmination of our effort in the development of a next generation optimization software. As an optimization software designed with define-by-run principle, Optuna is particularly the first of its kind. We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications. Our software is available under the MIT license (https://github.com/pfnet/optuna/).
|
Year | DOI | Keywords |
|---|---|---|
2019 | 10.1145/3292500.3330701 | Bayesian optimization, black-box optimization, hyperparameter optimization, machine learning system |
Field | DocType | ISSN |
Hyperparameter optimization,Architecture,Computer science,Bayesian optimization,Software,Ranging,MIT License,Artificial intelligence,Scalable distributed,Machine learning,Distributed computing | Conference | 978-1-4503-6201-6 |
ISBN | Citations | PageRank |
978-1-4503-6201-6 | 39 | 1.49 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Takuya Akiba | 1 | 378 | 20.70 |
| Shotaro Sano | 2 | 40 | 2.18 |
| toshihiko yanase | 3 | 47 | 3.40 |
| Takeru Ohta | 4 | 39 | 1.49 |
| Masanori Koyama | 5 | 208 | 7.80 |