Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization

Ruoqian Liu; Ankit Agrawal; Wei Keng Liao; Alok Choudhary; Zhengzhang Chen

doi:10.1109/IC3.2015.7346645

Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization

Ruoqian Liu, Ankit Agrawal, Wei Keng Liao, Alok Choudhary, Zhengzhang Chen

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Searching for solutions that optimize a continuous function can be difficult due to the infinite search space, and can be further complicated by the high dimensionality in the number of variables and complexity in the structure of constraints. Both deterministic and stochastic methods have been presented in the literature with a purpose of exploiting the search space and avoiding local optima as much as possible. In this research, we develop a machine learning framework aiming to 'prune' the search effort of both types of optimization techniques by developing meta-heuristics, attempting to knowledgeably reordering the search space and reducing the search region. Numerical examples demonstrate that this approach can effectively find the global optimal solutions and significantly reduce the computational time for seven benchmark problems with variable dimensions of 100, 500 and 1000, compared to Genetic Algorithms.

Original language	English (US)
Title of host publication	2015 8th International Conference on Contemporary Computing, IC3 2015
Editors	J. Amudha, Deepa Gupta, Jaric Zola, Narendra Nanjangud, Animesh Pathak, Sushil K. Prasad, Tirumale Ramesh, Manish Parashar, Kishore Kothapalli, Purushotham Bangalore, Sanjay Chaudhary, K. V. Dinesha
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	13-18
Number of pages	6
ISBN (Electronic)	9781467379489
DOIs	https://doi.org/10.1109/IC3.2015.7346645
State	Published - Dec 3 2015
Event	8th International Conference on Contemporary Computing, IC3 2015 - Noida, India Duration: Aug 20 2015 → Aug 22 2015

Publication series

Name	2015 8th International Conference on Contemporary Computing, IC3 2015

Other

Other	8th International Conference on Contemporary Computing, IC3 2015
Country/Territory	India
City	Noida
Period	8/20/15 → 8/22/15

Keywords

Complexity reduction
Constrained optimization
Machine learning
Meta-heuristics

ASJC Scopus subject areas

Software

Access to Document

10.1109/IC3.2015.7346645

Cite this

Liu, R., Agrawal, A., Liao, W. K., Choudhary, A., & Chen, Z. (2015). Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization. In J. Amudha, D. Gupta, J. Zola, N. Nanjangud, A. Pathak, S. K. Prasad, T. Ramesh, M. Parashar, K. Kothapalli, P. Bangalore, S. Chaudhary, & K. V. Dinesha (Eds.), 2015 8th International Conference on Contemporary Computing, IC3 2015 (pp. 13-18). [7346645] (2015 8th International Conference on Contemporary Computing, IC3 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IC3.2015.7346645

Liu, Ruoqian ; Agrawal, Ankit ; Liao, Wei Keng et al. / Pruned search : A machine learning based meta-heuristic approach for constrained continuous optimization. 2015 8th International Conference on Contemporary Computing, IC3 2015. editor / J. Amudha ; Deepa Gupta ; Jaric Zola ; Narendra Nanjangud ; Animesh Pathak ; Sushil K. Prasad ; Tirumale Ramesh ; Manish Parashar ; Kishore Kothapalli ; Purushotham Bangalore ; Sanjay Chaudhary ; K. V. Dinesha. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 13-18 (2015 8th International Conference on Contemporary Computing, IC3 2015).

@inproceedings{109e64f80c1a41b39fe2448b16ee82dc,

title = "Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization",

abstract = "Searching for solutions that optimize a continuous function can be difficult due to the infinite search space, and can be further complicated by the high dimensionality in the number of variables and complexity in the structure of constraints. Both deterministic and stochastic methods have been presented in the literature with a purpose of exploiting the search space and avoiding local optima as much as possible. In this research, we develop a machine learning framework aiming to 'prune' the search effort of both types of optimization techniques by developing meta-heuristics, attempting to knowledgeably reordering the search space and reducing the search region. Numerical examples demonstrate that this approach can effectively find the global optimal solutions and significantly reduce the computational time for seven benchmark problems with variable dimensions of 100, 500 and 1000, compared to Genetic Algorithms.",

keywords = "Complexity reduction, Constrained optimization, Machine learning, Meta-heuristics",

author = "Ruoqian Liu and Ankit Agrawal and Liao, {Wei Keng} and Alok Choudhary and Zhengzhang Chen",

note = "Funding Information: ACKNOWLEDGEMENT: This work is supported in part by the following grants: AFOSR award FA9550-12-1-0458; NIST award 70NANB14H012; NSF awards CCF-1029166, IIS-1343639, CCF-1409601; DOE award DESC0007456. Publisher Copyright: {\textcopyright} 2015 IEEE.; 8th International Conference on Contemporary Computing, IC3 2015 ; Conference date: 20-08-2015 Through 22-08-2015",

year = "2015",

month = dec,

day = "3",

doi = "10.1109/IC3.2015.7346645",

language = "English (US)",

series = "2015 8th International Conference on Contemporary Computing, IC3 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "13--18",

editor = "J. Amudha and Deepa Gupta and Jaric Zola and Narendra Nanjangud and Animesh Pathak and Prasad, {Sushil K.} and Tirumale Ramesh and Manish Parashar and Kishore Kothapalli and Purushotham Bangalore and Sanjay Chaudhary and Dinesha, {K. V.}",

booktitle = "2015 8th International Conference on Contemporary Computing, IC3 2015",

address = "United States",

}

Liu, R, Agrawal, A , Liao, WK , Choudhary, A & Chen, Z 2015, Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization. in J Amudha, D Gupta, J Zola, N Nanjangud, A Pathak, SK Prasad, T Ramesh, M Parashar, K Kothapalli, P Bangalore, S Chaudhary & KV Dinesha (eds), 2015 8th International Conference on Contemporary Computing, IC3 2015., 7346645, 2015 8th International Conference on Contemporary Computing, IC3 2015, Institute of Electrical and Electronics Engineers Inc., pp. 13-18, 8th International Conference on Contemporary Computing, IC3 2015, Noida, India, 8/20/15. https://doi.org/10.1109/IC3.2015.7346645

Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization. / Liu, Ruoqian; Agrawal, Ankit ; Liao, Wei Keng et al.
2015 8th International Conference on Contemporary Computing, IC3 2015. ed. / J. Amudha; Deepa Gupta; Jaric Zola; Narendra Nanjangud; Animesh Pathak; Sushil K. Prasad; Tirumale Ramesh; Manish Parashar; Kishore Kothapalli; Purushotham Bangalore; Sanjay Chaudhary; K. V. Dinesha. Institute of Electrical and Electronics Engineers Inc., 2015. p. 13-18 7346645 (2015 8th International Conference on Contemporary Computing, IC3 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Pruned search

T2 - 8th International Conference on Contemporary Computing, IC3 2015

AU - Liu, Ruoqian

AU - Agrawal, Ankit

AU - Liao, Wei Keng

AU - Choudhary, Alok

AU - Chen, Zhengzhang

N1 - Funding Information: ACKNOWLEDGEMENT: This work is supported in part by the following grants: AFOSR award FA9550-12-1-0458; NIST award 70NANB14H012; NSF awards CCF-1029166, IIS-1343639, CCF-1409601; DOE award DESC0007456. Publisher Copyright: © 2015 IEEE.

PY - 2015/12/3

Y1 - 2015/12/3

N2 - Searching for solutions that optimize a continuous function can be difficult due to the infinite search space, and can be further complicated by the high dimensionality in the number of variables and complexity in the structure of constraints. Both deterministic and stochastic methods have been presented in the literature with a purpose of exploiting the search space and avoiding local optima as much as possible. In this research, we develop a machine learning framework aiming to 'prune' the search effort of both types of optimization techniques by developing meta-heuristics, attempting to knowledgeably reordering the search space and reducing the search region. Numerical examples demonstrate that this approach can effectively find the global optimal solutions and significantly reduce the computational time for seven benchmark problems with variable dimensions of 100, 500 and 1000, compared to Genetic Algorithms.

AB - Searching for solutions that optimize a continuous function can be difficult due to the infinite search space, and can be further complicated by the high dimensionality in the number of variables and complexity in the structure of constraints. Both deterministic and stochastic methods have been presented in the literature with a purpose of exploiting the search space and avoiding local optima as much as possible. In this research, we develop a machine learning framework aiming to 'prune' the search effort of both types of optimization techniques by developing meta-heuristics, attempting to knowledgeably reordering the search space and reducing the search region. Numerical examples demonstrate that this approach can effectively find the global optimal solutions and significantly reduce the computational time for seven benchmark problems with variable dimensions of 100, 500 and 1000, compared to Genetic Algorithms.

KW - Complexity reduction

KW - Constrained optimization

KW - Machine learning

KW - Meta-heuristics

UR - http://www.scopus.com/inward/record.url?scp=84969131073&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969131073&partnerID=8YFLogxK

U2 - 10.1109/IC3.2015.7346645

DO - 10.1109/IC3.2015.7346645

M3 - Conference contribution

AN - SCOPUS:84969131073

T3 - 2015 8th International Conference on Contemporary Computing, IC3 2015

SP - 13

EP - 18

BT - 2015 8th International Conference on Contemporary Computing, IC3 2015

A2 - Amudha, J.

A2 - Gupta, Deepa

A2 - Zola, Jaric

A2 - Nanjangud, Narendra

A2 - Pathak, Animesh

A2 - Prasad, Sushil K.

A2 - Ramesh, Tirumale

A2 - Parashar, Manish

A2 - Kothapalli, Kishore

A2 - Bangalore, Purushotham

A2 - Chaudhary, Sanjay

A2 - Dinesha, K. V.

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 20 August 2015 through 22 August 2015

ER -

Liu R, Agrawal A , Liao WK , Choudhary A, Chen Z. Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization. In Amudha J, Gupta D, Zola J, Nanjangud N, Pathak A, Prasad SK, Ramesh T, Parashar M, Kothapalli K, Bangalore P, Chaudhary S, Dinesha KV, editors, 2015 8th International Conference on Contemporary Computing, IC3 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 13-18. 7346645. (2015 8th International Conference on Contemporary Computing, IC3 2015). doi: 10.1109/IC3.2015.7346645

Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this