DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DHD2GUN2record.jsonopen to challenge →
read the original abstract
Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. Here, we combine the advantages of the popular bandit-based HPO method Hyperband (HB) and the evolutionary search approach of Differential Evolution (DE) to yield a new HPO method which we call DEHB. Comprehensive results on a very broad range of HPO problems, as well as a wide range of tabular benchmarks from neural architecture search, demonstrate that DEHB achieves strong performance far more robustly than all previous HPO methods we are aware of, especially for high-dimensional problems with discrete input dimensions. For example, DEHB is up to 1000x faster than random search. It is also efficient in computational time, conceptually simple and easy to implement, positioning it well to become a new default HPO method.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Zoom, Don't Wander: Why Regional Search Outperforms Pareto Reasoning and Global Optimization in Budget-Constrained SBSE
A minimal greedy regional zoom method outperforms Pareto and global Bayesian optimization in budget-constrained SBSE, winning or tying in 84-89% of cases at equal budget and even at one-fifth budget, because optimal s...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.