MetaGrad: Multiple Learning Rates in Online Learning

Tim van Erven, Wouter M. Koolen

Neural Information Processing Systems 

MetaGrad's main feature is that it simultaneously considers multiple learning rates. Unlike previous methods with provable regret guarantees, however, its learning rates are not monotonically decreasing over time and are not tuned based on a theoretically derived bound on the regret.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found