Algorithm Selection: From Meta-Learning to Hyper-Heuristics

Cruz-Reyes, Laura; Gómez-Santillán, Claudia; Pérez-Ortega, Joaquín; Landero, Vanesa; Quiróz-Castellanos, Marcela; Ochoa, Alberto

doi:10.5772/36710

Cited by 11 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some approaches adopt Rice's framework (Rice, 1976) for solving the AS problem to learn from the algorithms experience in solving different problems (Kerschke, et al, 2018). Most of these approaches use Rice's features-based model to solve the AS (Cruz-Reyes, et al, 2012) and the AC (Belkhir, et al, 2017) problems. Most of these approaches depict the AS and the AC problems as two separated problems in spite of the strong relations between them (Janković & Doerr, 2019).…”

Section: A Simple Algorithm Selector For Continuous Optimisation Prob...mentioning

confidence: 99%

Digital Twins for Lighting Analysis: Literature Review, Challenges, and Research Opportunities

Hassan¹,

Angelaki²,

Alfaro³

et al. 2022

ECMS 2022 Proceedings Edited by Ibrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat

View full text Add to dashboard Cite

Light modelling, simulation, and photometric calculations are by now common tasks in the lighting design process. These practices contribute to the definition and comparison of suitable layout arrangements and help predict the impact of lighting devices. Those tasks demand the use of tools to support the simulation of different scenarios, the analyses of their pros and cons according to different criteria (e.g., health and safety, perception, aesthetics, energy consumption, and costs), and decision-making. Digital twins have emerged as relevant technologies to simulate and visualize different ``what-if'' scenarios associated with physical entities and processes. In this paper, we investigate the state-of-the-art research concerning the use of digital twins for supporting lighting analysis in the urban/outdoor context. We also present and discuss challenges and research opportunities related to the design, implementation, and validation of digital twins in this domain.

show abstract

Section: A Simple Algorithm Selector For Continuous Optimisation Prob...mentioning

confidence: 99%

Digital Twins for Lighting Analysis: Literature Review, Challenges, and Research Opportunities

Hassan¹,

Angelaki²,

Alfaro³

et al. 2022

ECMS 2022 Proceedings Edited by Ibrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat

View full text Add to dashboard Cite

show abstract

“…The traditional method of dealing with ASP is to hand-design features and then extract them from the instance data. Here, we use a set of features collated from multiple papers in the literature where algorithm-selection methods have been applied to bin-packing (Cruz-Reyes et al, 2012;López-Camacho et al, 2013;Brownlee et al, 2018) (Brownlee et al, 2018); 7. The ratio of small items of size ω ≤ C/4 (Ross et al, 2002); 8.…”

Section: Definition Of Featuresmentioning

confidence: 99%

Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches

Alissa¹,

Sim²,

Hart³

2022

Preprint

View full text Add to dashboard Cite

We propose a novel technique for algorithm-selection, applicable to optimisation domains in which there is implicit sequential information encapsulated in the data, e.g., in online bin-packing. Specifically we train two types of recurrent neural networks to predict a packing heuristic in online binpacking, selecting from four well-known heuristics. As input, the RNN methods only use the sequence of item-sizes. This contrasts to typical approaches to algorithm-selection which require a model to be trained using domain-specific instance features that need to be first derived from the input data. The RNN approaches are shown to be capable of achieving within 5% of the oracle performance on between 80.88% to 97.63% of the instances, depending on the dataset. They are also shown to outperform classical machine learning models trained using derived features. Finally, we hypothesise that the proposed methods perform well when the instances exhibit some implicit structure that results in discriminatory performance with respect to a set of heuristics. We test this hypothesis by generating fourteen new datasets with increasing levels of structure, and show that there is a critical threshold of structure required before algorithm-selection delivers benefit.

show abstract

Section: A Simple Algorithm Selector For Continuous Optimisation Prob...mentioning

confidence: 99%

ECMS 2022 Proceedings edited by Ibrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat

2022

View full text Add to dashboard Cite

NTNU is a university with an international focus, with headquarters in Trondheim and campuses in Ålesund and Gjøvik. NTNU has a main profile in science and technology, a variety of programmes of professional study, and great academic breadth that also includes the humanities, social sciences, economics, medicine, health sciences, educational science, architecture, entrepreneurship, art disciplines and artistic activities. NTNU has eight faculties, 55 departments, and NTNU University Museum with a total budget of NOK 10 billion, of which NOK 2,6 billion from external sources (2021). NTNU offers 356 study programs, as well as further education to more than 42000 from Norway and abroad enrolled in various bachelor, master, and PhD programs.NTNU in its current form was established by the King-in-Council in 1996 by the merger of the former University of Trondheim and other university-level institutions, with roots dating back to 1760, and has later also incorporated some former university colleges.NTNU is consistently ranked in the top one percentage among the world's universities, We are honored to offer, besides the scientific program of the conference, consisting in more than 45 high quality accepted papers in 8 scientific tracks, a rich and various series of social events, as usual for the spirit of this conference.

show abstract

Algorithm Selection: From Meta-Learning to Hyper-Heuristics

Cited by 11 publications

References 40 publications

Digital Twins for Lighting Analysis: Literature Review, Challenges, and Research Opportunities

Digital Twins for Lighting Analysis: Literature Review, Challenges, and Research Opportunities

Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches

ECMS 2022 Proceedings edited by Ibrahim A. Hameed, Agus Hasan, Saleh Abdel-Afou Alaliyat

Contact Info

Product

Resources

About