Surrogate Benchmarks for Hyperparameter Optimization

By Katharina Eggensperger, Frank Hutter, Holger H. Hoos, Kevin Leyton-Brown. 2014

17 citations recorded by the source corpus.

Subfields: Evaluation & Benchmarks, Neural Architecture Search & AutoML

How researchers see this paper

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

In Evaluation & Benchmarks

1. Frank Hutter
2. Holger H. Hoos
3. Aaron Klein
4. Kaiyong Zhao
5. Xiaowen Chu
6. Xin He
7. Kevin Leyton-Brown
8. Katharina Eggensperger

In Neural Architecture Search & AutoML

1. Frank Hutter
2. Holger H. Hoos
3. Kevin Leyton-Brown
4. Katharina Eggensperger
5. Aaron Klein
6. Xin He
7. Xiaowen Chu
8. Kaiyong Zhao

Citations in the corpus

• AutoML: A Survey of the State-of-the-Art (2019, methodology): “Surrogate-based method [120]–[122] is another powerful tool that approximates to the black box function.”
• Efficient Benchmarking of Hyperparameter Optimizers via Surrogates (2015, background): “…under different selected hyperparameters, our benchmarks can also substantially reduce the 1This paper is an extended and improved version of a paper presented at an ECAI workshop (Eggensperger et al. 2014). time required for running a hyperparameter optimizer, facilitating whitebox tests.”
• Tunability: Importance of Hyperparameters of Machine Learning Algorithms (2018, methodology): “In the following we use random forest as surrogate model because it performs reasonably well and is already an established algorithm for surrogate models in the literature (Eggensperger et al., 2014; Hutter et al., 2013).”