Making Learners (More) Monotone

no code implementations • 25 Nov 2019 • Tom J. Viering, Alexander Mey, Marco Loog

Learning performance can show non-monotonic behavior.

Nuclear Discrepancy for Active Learning

no code implementations • 8 Jun 2017 • Tom J. Viering, Jesse H. Krijthe, Marco Loog

In particular we show the relation between the bound of the state-of-the-art Maximum Mean Discrepancy (MMD) active learner, the bound of the Discrepancy, and a new and looser bound that we refer to as the Nuclear Discrepancy bound.

Active Learning Generalization Bounds