Combining Gaussian Processes with Neural Networks for Active Learning in Optimization

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F21%3A00555604" target="_blank" >RIV/67985807:_____/21:00555604 - isvavai.cz</a>

Result on the web

<a href="http://ceur-ws.org/Vol-3079/ial2021_paper9.pdf" target="_blank" >http://ceur-ws.org/Vol-3079/ial2021_paper9.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Combining Gaussian Processes with Neural Networks for Active Learning in Optimization

Original language description

One area where active learning plays an important role is black-box optimization of objective functions with expensive evaluations. To deal with such evaluations, continuous black-box optimization has adopted an approach called surrogate modelling or metamodelling, which consists in replacing the true black-box objective in some of its evaluations with a suitable regression model, the selection of evaluations for replacement being an active learning task. This paper concerns surrogate modelling in the context of a surrogate-assisted variant of the continuous black-box optimizer Covariance Matrix Adaptation Evolution Strategy. It reports the experimental investigation of surrogate models combining artificial neural networks with Gaussian processes, for which it considers six different covariance functions. The experiments were performed on the set of 24 noiseless benchmark functions of the platform Comparing Continuous Optimizers COCO with 5 different dimensionalities. Their results revealed that the most suitable covariance function for this combined kind of surrogate models is the rational quadratic followed by the Matérn 25 and squared exponential. Moreover, the rational quadratic and squared exponential covariances were found interchangeable in the sense that for no function, no group of functions, no dimension and combination of them, the performance of the respective surrogate models was significantly different.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA18-18080S" target="_blank" >GA18-18080S: Fusion-Based Knowledge Discovery in Human Activity Data</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

IAL@ECML PKDD 2021: Workshop on Interactive Adaptive Learning. Proceedings

ISBN

—

ISSN

1613-0073

e-ISSN

—

Number of pages

16

Pages from-to

105-120

Publisher name

Technical University & CreateSpace Independent Publishing

Place of publication

Aachen

Event location

Bilbao / virtual

Event date

Sep 13, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—