Abstract
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 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 are possible
Original language | English |
---|---|
Title of host publication | NIPS'18 |
Subtitle of host publication | Proceedings of the 32nd International Conference on Neural Information Processing Systems |
Editors | S. Bengio, H.M. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi |
Publisher | Curran Associates, Inc. |
Pages | 1793-1802 |
Number of pages | 10 |
Publication status | Published - 2018 |
Event | NIPS 2018: 32nd Conference on Neural Information Processing Systems - Montréal, Canada Duration: 3 Dec 2018 → 8 Dec 2018 Conference number: 32 |
Conference
Conference | NIPS 2018 |
---|---|
Country/Territory | Canada |
City | Montréal |
Period | 3/12/18 → 8/12/18 |