AI Paper Atlas

Research map / Probabilistic and scientific modeling / Bayesian optimization

Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar

JMLR 2018 · Probabilistic and scientific modeling › Bayesian optimization · approach: Multi-fidelity hyperparameter optimization · 2,001 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Hyperband instead of random search/Bayesian optimizationdeep-network tuning · CIFAR-10speedup: over 20x faster than random searchImproved
use Hyperband instead of SMAC (early)deep-network tuning · MRBIspeedup: 5x faster than SMAC (early)Improved
use Hyperband instead of SMAC (early)deep-network tuning · SVHNtest errorHurt
repeat only the most aggressive bracket s=4 instead of full Hyperband (ablation)Hyperband · CIFAR-10 and MRBItest errorImproved
use infinite horizon instead of finite horizon Hyperband (ablation)Hyperband · CIFAR-10test error within 50RHurt
use Hyperband with data subsampling instead of random searchHyperband · 117 datasetstest error rankMixed
use random 2x instead of Hyperbandrandom search · 117 datasetstest error rankImproved
use Hyperband instead of other searchers on selected datasetsHyperband · 21 of 117 datasetstest error rankImproved
use Hyperband instead of Bayesian optimizationkernel classifier · Kernel least squares CIFAR-10speedup: over 30x faster than Bayesian optimization, 70x faster than random searchImproved
use Hyperband instead of random searchrandom feature kernel · Random feature kernel approximationspeedup: around 6x fasterImproved
use Hyperband instead of random search with brackets s=0Hyperband · Appendix LeNet (R=81, eta=3)test errorImproved

Later papers that compared with this method

3 later accepted papers report Hyperband as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy