ADAPTIVE SEQUENTIAL INTERPOLATOR USING ACTIVE LEARNING FOR EFFICIENT EMULATION OF COMPLEX SYSTEMS

被引：0

作者：

Martino, Luca ^{[3
]}

Svendsen, Daniel Heestermans ^{[1
]}

Vicent, Jorge ^{[1
,2
]}

Camps-Valls, Gustau ^{[1
]}

机构：

[1] Univ Valencia, Image Proc Lab IPL, Valencia, Spain

[2] Magellium Co Geoinformat & Image Proc, Toulouse, France

[3] Univ Rey Juan Carlos, Dept Signal Proc, Madrid, Spain

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2020年

基金：

欧洲研究理事会;

关键词：

Adaptive interpolation; active learning; Bayesian optimization; experimental design; EXPERIMENTAL-DESIGN;

D O I：

10.1109/icassp40776.2020.9053372

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Many fields of science and engineering require the use of complex and computationally expensive models to understand the involved processes in the system of interest. Nevertheless, due to the high cost involved, the required study becomes a cumbersome process. This paper introduces an interpolation procedure which belongs to the family of active learning algorithms, in order to construct cheap surrogate models of such costly complex systems. The proposed technique is sequential and adaptive, and is based on the optimization of a suitable acquisition function. We illustrate its efficiency in a toy example and for the construction of an emulator of an atmosphere modeling system.

引用

页码：3577 / 3581

页数：5

共 23 条

[1]

[Anonymous], 2016, IEEE GEOSC REM SEN M

[2]

Ascher Uri M, 2011, A First Course in Numerical Methods, P26, DOI DOI 10.1137/9780898719987

[3]

Berk A., 2006, MODTRAN5: 2006 update

[4] Hierarchical adaptive experimental design for Gaussian process emulators [J].