Lissovoi, A., Oliveto, P. and Warwicker, J.A. (2020) How the duration of the learning period affects the performance of random gradient selection hyper-heuristics. In: Proceedings of the AAAI Conference on Artificial Intelligence. Thirty-Fourth AAAI Conference on Artificial Intelligence, 07-12 Feb 2020, New York, NY, USA. Association for the Advancement of Artificial Intelligence (AAAI) , pp. 2376-2383.
Abstract
Recent analyses have shown that a random gradient hyper-heuristic (HH) using randomised local search (RLSk) low-level heuristics with different neighbourhood sizes k can optimise the unimodal benchmark function LeadingOnes in the best expected time achievable with the available heuristics, if sufficiently long learning periods τ are employed. In this paper, we examine the impact of the learning period on the performance of the hyper-heuristic for standard unimodal benchmark functions with different characteristics: Ridge, where the HH has to learn that RLS1 is always the best low-level heuristic, and OneMax, where different low-level heuristics are preferable in different areas of the search space. We rigorously prove that super-linear learning periods τ are required for the HH to achieve optimal expected runtime for Ridge. Conversely, a sub-logarithmic learning period is the best static choice for OneMax, while using super-linear values for τ increases the expected runtime above the asymptotic unary unbiased black box complexity of the problem. We prove that a random gradient HH which automatically adapts the learning period throughout the run has optimal asymptotic expected runtime for both OneMax and Ridge. Additionally, we show experimentally that it outperforms any static learning period for realistic problem sizes.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2020 AAAI. |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Funding Information: | Funder Grant number Engineering and Physical Science Research Council EP/M004252/1 |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 17 Jul 2020 06:47 |
Last Modified: | 17 Jul 2020 06:47 |
Status: | Published |
Publisher: | Association for the Advancement of Artificial Intelligence (AAAI) |
Refereed: | Yes |
Identification Number: | 10.1609/aaai.v34i03.5617 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:163366 |