Timezone: »
Poster
The Pessimistic Limits and Possibilities of Margin-based Losses in Semi-supervised Learning
Jesse Krijthe · Marco Loog
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.
Author Information
Jesse Krijthe (Radboud University Nijmegen)
Marco Loog (Delft University of Technology)
More from the Same Authors
-
2019 : Poster Spotlights »
Théophile Griveau-Billion · Rahul Singh · Zichen Zhang · Ciarán Lee · Jesse Krijthe · Grace Charles · Vira Semenova · Rahul Ladhania · Miruna Oprescu -
2019 : Coffee break, posters, and 1-on-1 discussions »
Yangyi Lu · Daniel Chen · Hongseok Namkoong · Marie Charpignon · Maja Rudolph · Amanda Coston · Julius von Kügelgen · Niranjani Prasad · Paramveer Dhillon · Yunzong Xu · Yixin Wang · Alexander Markham · David Rohde · Rahul Singh · Zichen Zhang · Negar Hassanpour · Ankit Sharma · Ciarán Lee · Jean Pouget-Abadie · Jesse Krijthe · Divyat Mahajan · Nan Rosemary Ke · Peter Wirnsberger · Vira Semenova · Dmytro Mykhaylov · Dennis Shen · Kenta Takatsu · Liyang Sun · Jeremy Yang · Alexander Franks · Pak Kan Wong · Tauhid Zaman · Shira Mitchell · min kyoung kang · Qi Yang -
2019 Poster: Minimizers of the Empirical Risk and Risk Monotonicity »
Marco Loog · Tom Viering · Alexander Mey