Speeding up Hyper-parameter Optimization by Extrapolation of Learning Curves Using Previous Builds

35 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Comprehensive Survey of Neural Architecture Search (2020, methodology): “Similar strategies are also used to solve hyperparameter optimization problems [89, 108].”
A Survey on Neural Architecture Search (2019, methodology): “ng rate violates the assumption that the learning curve is a quickly saturating function and a cyclic learning rate schedule violates the assumption that the learning curve is an increasing function. Chandrashekaran and Lane (2017) overcome this problem by using mature learning curves observed durin”
Meta-Learning: A Survey (2018, neutral): “Learning curves are used extensively to speed up hyperparameter optimization on a given task (Kohavi and John, 1995; Provost et al., 1999; Swersky et al., 2014; Chandrashekaran and Lane, 2017).”
Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning (2020, background): “, 2020), solutions for specific model classes (Swersky et al., 2014; Domhan et al., 2015; Chandrashekaran and Lane, 2017) and selecting a fidelity value from a continuous range (Klein et al.”