dc.contributor.author | Graux, Damien | |
dc.contributor.author | Payrosangari, Samin | |
dc.contributor.author | Sadeghi, Afshin | |
dc.contributor.author | Lehmann, Jens | |
dc.date.accessioned | 2020-11-30T09:26:06Z | |
dc.date.available | 2020-11-30T09:26:06Z | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020 | en |
dc.identifier.citation | Payrosangari S., Sadeghi A., Graux D., Lehmann J. (2020) Meta-hyperband: Hyperparameter Optimization with Meta-learning and Coarse-to-Fine. In: Analide C., Novais P., Camacho D., Yin H. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2020. IDEAL 2020. Lecture Notes in Computer Science, vol 12490. Springer, Cham | en |
dc.identifier.other | Y | |
dc.description | PUBLISHED | en |
dc.description.abstract | Hyperparameter optimization is one of the main pillars of machine learning algorithms. In this paper, we introduce Meta-Hyperband: a Hyperband based algorithm that improves the hyperparameter optimization by adding levels of exploitation. Unlike Hyperband method, which is a pure exploration bandit-based approach for hyperparameter optimization, our meta approach generates a trade-off between exploration and exploitation by combining the Hyperband method with meta-learning and Coarse-to-Fine modules. We analyze the performance of Meta-Hyperband on various datasets to tune the hyperparameters of CNN and SVM. The experiments indicate that in many cases Meta-Hyperband can discover hyperparameter configurations with higher quality than Hyperband, using similar amounts of resources. In particular, we discovered a CNN configuration for classifying CIFAR10 dataset which has a 3% higher performance than the configuration founded by Hyperband, and is also 0.3% more accurate than the best-reported configuration of the Bayesian optimization approach. Additionally, we release a publicly available pool of historically well-performed configurations on several datasets for CNN and SVM to ease the adoption of Meta-Hyperband. | en |
dc.language.iso | en | en |
dc.rights | N | en |
dc.subject | Hyperparameter optim | en |
dc.subject | Meta-learning | en |
dc.subject | Coarse-to-Fine | en |
dc.title | Meta-Hyperband: Hyperparameter optimization with meta-learning and Coarse-to-Fine | en |
dc.type | Conference Paper | en |
dc.type.supercollection | scholarly_publications | en |
dc.type.supercollection | refereed_publications | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/grauxd | |
dc.identifier.rssinternalid | 221692 | |
dc.identifier.doi | https://doi.org/10.1007/978-3-030-62365-4_32 | en |
dc.rights.ecaccessrights | openAccess | |
dc.subject.TCDTag | MACHINE LEARNING | en |
dc.subject.TCDTag | OPTIMISATION | en |
dc.identifier.rssuri | https://dgraux.github.io/publications/Metahyperband_IDEAL_2020.pdf | |
dc.subject.darat_thematic | Communication | en |
dc.status.accessible | N | en |
dc.contributor.sponsor | Marie Curie | en |
dc.contributor.sponsorGrantNumber | 801522 | en |
dc.contributor.sponsor | Science Foundation Ireland (SFI) | en |
dc.contributor.sponsorGrantNumber | 13/RC/2106 | en |
dc.identifier.uri | http://hdl.handle.net/2262/94274 | |