Abstract
The paradigm of Learning Under Privileged Information (LUPI) was used in various prac- tical applications, including its combination with Conformal Prediction (CP) framework. In this note, we discuss possible sources and limitations of its efficiency. We try to argue that accuracy improvement coming from using privileged information is not occasional. For this goal, we consider some minimalistic models of LUPI where the contribution of the privileged information appears in its noise-free essence. Then, we discuss connection of LUPI paradigm and CP framework in relation with the models.
Original language | English |
---|---|
Title of host publication | 11th Symposium on Conformal and Probabilistic Prediction with Applications |
Place of Publication | Brighton, UK |
Publisher | Proceedings of Machine Learning Research, 2022 Conformal and Probabilistic Prediction and Applications |
Number of pages | 14 |
Volume | 179 |
Publication status | Published - 25 Aug 2022 |
Keywords
- Conformal prediction
- privileged information
- efficiency