Skip to yearly menu bar Skip to main content


Poster

Optimizer Benchmarking Needs to Account for Hyperparameter Tuning

Prabhu Teja Sivaprasad · Florian Mai · Thijs Vogels · Martin Jaggi · François Fleuret

Virtual

Keywords: [ Optimization ] [ Meta-learning and Automated ML ] [ Other ] [ Deep Learning - General ]


Abstract:

The performance of optimizers, particularly in deep learning, depends considerably on their chosen hyperparameter configuration. The efficacy of optimizers is often studied under near-optimal problem-specific hyperparameters, and finding these settings may be prohibitively costly for practitioners. In this work, we argue that a fair assessment of optimizers' performance must take the computational cost of hyperparameter tuning into account, i.e., how easy it is to find good hyperparameter configurations using an automatic hyperparameter search. Evaluating a variety of optimizers on an extensive set of standard datasets and architectures, our results indicate that Adam is the most practical solution, particularly in low-budget scenarios.

Chat is not available.