On efficiency of Learning Under Privileged Information

Ilia Nouretdinov
Proceedings of the Eleventh Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 179:239-252, 2022.

Abstract

The paradigm of Learning Under Privileged Information (LUPI) was used in various practical 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v179-nouretdinov22a, title = {On efficiency of Learning Under Privileged Information}, author = {Nouretdinov, Ilia}, booktitle = {Proceedings of the Eleventh Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {239--252}, year = {2022}, editor = {Johansson, Ulf and Boström, Henrik and An Nguyen, Khuong and Luo, Zhiyuan and Carlsson, Lars}, volume = {179}, series = {Proceedings of Machine Learning Research}, month = {24--26 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v179/nouretdinov22a/nouretdinov22a.pdf}, url = {https://proceedings.mlr.press/v179/nouretdinov22a.html}, abstract = {The paradigm of Learning Under Privileged Information (LUPI) was used in various practical 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.} }
Endnote
%0 Conference Paper %T On efficiency of Learning Under Privileged Information %A Ilia Nouretdinov %B Proceedings of the Eleventh Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2022 %E Ulf Johansson %E Henrik Boström %E Khuong An Nguyen %E Zhiyuan Luo %E Lars Carlsson %F pmlr-v179-nouretdinov22a %I PMLR %P 239--252 %U https://proceedings.mlr.press/v179/nouretdinov22a.html %V 179 %X The paradigm of Learning Under Privileged Information (LUPI) was used in various practical 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.
APA
Nouretdinov, I.. (2022). On efficiency of Learning Under Privileged Information. Proceedings of the Eleventh Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 179:239-252 Available from https://proceedings.mlr.press/v179/nouretdinov22a.html.

Related Material