OPENBOX: A Generalized Black-box Optimization Service

被引：44

作者：

Li, Yang ^{[1
]}

Shen, Yu ^{[1
,6
]}

Zhang, Wentao ^{[1
]}

Chen, Yuanwei ^{[1
]}

Jiang, Huaijun ^{[1
,6
]}

Liu, Mingchao ^{[1
]}

Jiang, Jiawei ^{[2
]}

Gao, Jinyang ^{[5
]}

Wu, Wentao ^{[4
]}

Yang, Zhi ^{[1
]}

Zhang, Ce ^{[2
]}

Cui, Bin ^{[1
,3
]}

机构：

[1] Peking Univ, Sch EECS, Key Lab High Confidence Software Technol MOE, Beijing, Peoples R China

[2] Swiss Fed Inst Technol, Dept Comp Sci, Syst Grp, Zurich, Switzerland

[3] Peking Univ Qingdao, Inst Computat Social Sci, Qingdao, Peoples R China

[4] Microsoft Res, Redmond, WA USA

[5] Alibaba Grp, Hangzhou, Peoples R China

[6] Kuaishou Technol, Beijing, Peoples R China

来源：

KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING | 2021年

关键词：

Bayesian Optimization; Black-box Optimization; BAYESIAN OPTIMIZATION; IMPROVEMENT; ALGORITHMS;

D O I：

10.1145/3447548.3467061

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design. However, it remains a challenge for users to apply BBO methods to their problems at hand with existing software packages, in terms of applicability, performance, and efficiency. In this paper, we build OPENBOX, an open-source and general-purpose BBO service with improved usability. The modular design behind OPENBOX also facilitates flexible abstraction and optimization of basic BBO components that are common in other existing systems. OPENBOX is distributed, fault-tolerant, and scalable. To improve efficiency, OPENBOX further utilizes "algorithm agnostic" parallelization and transfer learning. Our experimental results demonstrate the effectiveness and efficiency of OPENBOX compared to existing systems.

引用

页码：3209 / 3219

页数：11

共 48 条

[21] Modeling an Augmented Lagrangian for Blackbox Constrained Optimization [J].

Gramacy, Robert B. ;

Gray, Genetha A. ;

Le Digabel, Sebastien ;

Lee, Herbert K. H. ;

Ranjan, Pritam ;

Wells, Garth ;

Wild, Stefan M. .

TECHNOMETRICS, 2016, 58 (01) :1-11

[22] Constrained Bayesian optimization for automatic chemical design using variational autoencoders [J].

Griffiths, Ryan-Rhys ;

Hernandez-Lobato, Jose Miguel .

CHEMICAL SCIENCE, 2020, 11 (02) :577-586

[23]

Hansen N., 2001, COMPLETELY DERANDOMI

[24]

Hernández-Lobato JM, 2016, J MACH LEARN RES, V17

[25]

Hernández-Lobato JM, 2015, PR MACH LEARN RES, V37, P1699

[26]

Ho YC, 2001, IEEE DECIS CONTR P, P4409, DOI 10.1109/CDC.2001.980896

[27]

Hutter Frank, 2011, Learning and Intelligent Optimization. 5th International Conference, LION 5. Selected Papers, P507, DOI 10.1007/978-3-642-25566-3_40

[28]

Klein A., 2017, ICLR

[29]

Knowles Joshua, 2006, IEEE T EVOLUTIONARY

[30]

Knudde N, 2017, ARXIV171103845

← 1 2 3 4 5 →