2 papers
cs.LG2020
Do We Need Zero Training Loss After Achieving Zero Training Error?
Takashi Ishida, Ikko Yamane, Tomoya Sakai +2
Overparameterized deep networks have the capacity to memorize training data with zero \emph{training error}. Even after memorization, the \emph{training loss} continues to approach…
stat.ML2018
Uplift Modeling from Separate Labels
Ikko Yamane, Florian Yger, Jamal Atif +1
Uplift modeling is aimed at estimating the incremental impact of an action on an individual's behavior, which is useful in various application domains such as targeted marketing (a…