182 citations · 344 across the 9 of their papers we have counts for
4 papers · 1 filter
Automated Benchmark-Driven Design and Explanation of Hyperparameter Optimizers
Julia Moosbauer, Martin Binder, Lennart Schneider +5
Automated hyperparameter optimization (HPO) has gained great popularity and is an important ingredient of most automated machine learning frameworks. The process of designing HPO a…
YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimization
Florian Pfisterer, Lennart Schneider, Julia Moosbauer +2
When developing and analyzing new hyperparameter optimization methods, it is vital to empirically evaluate and compare them on well-curated benchmark suites. In this work, we propo…
Mutation is all you need
Lennart Schneider, Florian Pfisterer, Martin Binder +1
Neural architecture search (NAS) promises to make deep learning accessible to non-experts by automating architecture engineering of deep neural networks. BANANAS is one state-of-th…
Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges
Bernd Bischl, Martin Binder, Michel Lang +9
Most machine learning algorithms are configured by one or several hyperparameters that must be carefully chosen and often considerably impact performance. To avoid a time consuming…