Black Box Algorithm Selection by Convolutional Neural Network

Yaodong He; Shiu Yin Yuen

doi:10.1007/978-3-030-64580-9_23

Author(s)

Related Research Unit(s)

Department of Electrical Engineering

Detail(s)

Original language	English
Title of host publication	Machine Learning, Optimization, and Data Science
Subtitle of host publication	6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers
Editors	Giuseppe Nicosia, Varun Ojha, Emanuele La Malfa, Vincenzo Sciacca, Panos Pardalos, Giovanni Giuffrida, Renato Umeton
Place of Publication	Cham
Publisher	Springer
Pages	264-280
Volume	Part II
ISBN (Print)	9783030645793
Publication status	Published - Jul 2020

Publication series

Name	Lecture Notes in Computer Science
Volume	12566
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Title	6th International Conference on Machine Learning, Optimization, and Data Science (LOD 2020)
Location	Certosa di Pontignano
Place	Italy
City	Siena
Period	19 - 23 July 2020

Link(s)

DOI	DOI https://doi.org/10.1007/978-3-030-64580-9_23 Final Published version
	Check@CityULib
Link to Scopus	https://www.scopus.com/record/display.uri?eid=2-s2.0-85101339776&origin=recordpage
Permanent Link	https://scholars.cityu.edu.hk/en/publications/publication(8f5ab61c-b14d-417c-9d2b-26ea0ff989c4).html

Abstract

The no free lunch theorems inform us that no algorithm can beat others on all types of problems. Different types of optimization problems need different optimization algorithms. To deal with this issue, researchers propose algorithm selection to suggest the best optimization algorithm from the algorithm set for a given unknown optimization problem. Deep learning, which has been shown to perform well on various classification and regression tasks, is applied to the algorithm selection problem in this paper. Our deep learning architecture is based on convolutional neural network and follows the main architecture of visual geometry group. This architecture has been applied to many different types of 2-D data. Moreover, we also propose a novel method to extract landscape information from the optimization problems and save the information as 2-D images.

Research Area(s)

Algorithm selection, Black box optimization, Convolutional neural network, Deep learning, Optimization problems

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

[ RIS ] [ BibTeX ]

Black Box Algorithm Selection by Convolutional Neural Network. / He, Yaodong ; Yuen, Shiu Yin.

Machine Learning, Optimization, and Data Science: 6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers. ed. / Giuseppe Nicosia; Varun Ojha; Emanuele La Malfa; Vincenzo Sciacca; Panos Pardalos; Giovanni Giuffrida; Renato Umeton. Vol. Part II Cham : Springer, 2020. p. 264-280 (Lecture Notes in Computer Science; Vol. 12566).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 32_Refereed conference paper (with ISBN/ISSN) › peer-review

He, Y & Yuen, SY 2020, Black Box Algorithm Selection by Convolutional Neural Network. in G Nicosia, V Ojha, E La Malfa, V Sciacca, P Pardalos, G Giuffrida & R Umeton (eds), Machine Learning, Optimization, and Data Science: 6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers. vol. Part II, Lecture Notes in Computer Science, vol. 12566, Springer, Cham, pp. 264-280, 6th International Conference on Machine Learning, Optimization, and Data Science (LOD 2020), Siena, Italy, 19/07/20. https://doi.org/10.1007/978-3-030-64580-9_23

He, Y., & Yuen, S. Y. (2020). Black Box Algorithm Selection by Convolutional Neural Network. In G. Nicosia, V. Ojha, E. La Malfa, V. Sciacca, P. Pardalos, G. Giuffrida, & R. Umeton (Eds.), Machine Learning, Optimization, and Data Science: 6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers (Vol. Part II, pp. 264-280). (Lecture Notes in Computer Science; Vol. 12566). Springer. https://doi.org/10.1007/978-3-030-64580-9_23

He Y , Yuen SY. Black Box Algorithm Selection by Convolutional Neural Network. In Nicosia G, Ojha V, La Malfa E, Sciacca V, Pardalos P, Giuffrida G, Umeton R, editors, Machine Learning, Optimization, and Data Science: 6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers. Vol. Part II. Cham: Springer. 2020. p. 264-280. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-64580-9_23

He, Yaodong ; Yuen, Shiu Yin. / Black Box Algorithm Selection by Convolutional Neural Network. Machine Learning, Optimization, and Data Science: 6th International Conference, LOD 2020, Siena, Italy, July 19–23, 2020, Revised Selected Papers. editor / Giuseppe Nicosia ; Varun Ojha ; Emanuele La Malfa ; Vincenzo Sciacca ; Panos Pardalos ; Giovanni Giuffrida ; Renato Umeton. Vol. Part II Cham : Springer, 2020. pp. 264-280 (Lecture Notes in Computer Science).