Coarse-to-fine parameter tuning for content-based object categorization

Moshkelgosha, Vahid; Behzadi-Khormouji, Hamed; Yazdian-Dehkordi, Mahdi

doi:10.1109/pria.2017.7983038

Cited by 1 publication

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coarse-to-Fine: is a variation of the random search for hyperparameter optimization, which limits the space of possible hyperparameters configurations in an organized manner [12]. In pure random search, one picks many random configurations until reaching a high-quality model.…”

Section: Introductionmentioning

confidence: 99%

Meta-hyperband: Hyperparameter Optimization with Meta-learning and Coarse-to-Fine

Payrosangari

Sadeghi

Graux

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%