Poster
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning
Jesse Krijthe · Marco Loog
Room 517 AB #111
Keywords: [ Semi-Supervised Learning ] [ Classification ]
Consider a classification problem where we have both labeled and unlabeled data available. We show that for linear classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to construct \emph{any} semi-supervised approach that is able to guarantee an improvement over the supervised classifier measured by this surrogate loss on the labeled and unlabeled data. For convex margin-based loss functions that also increase, we demonstrate safe improvements \emph{are} possible.
Live content is unavailable. Log in and register to view live content