Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

By Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi, Franccois Fleuret Idiap Research Institute, Epfl. 2019

62 citations recorded by the source corpus.

Subfields: Optimization & Training

Citations in the corpus

• Sustainable AI: Environmental Implications, Challenges and Opportunities (2021, neutral): “Evaluations of optimization methods should account for all experimentation efforts required to tune optimizer hyperparameters, not just the method performance after tuning [59], [60].”