Vladimir Vovk, Valentina Fedorova, Ilia Nouretdinov, Alex Gammerman
Published 2016-03-14Version 1
We study optimal conformity measures for various criteria of efficiency in an idealized setting. This leads to an important class of criteria of efficiency that we call probabilistic; it turns out that the most standard criteria of efficiency used in literature on conformal prediction are not probabilistic.
Randomness, exchangeability, and conformal prediction
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
Privacy and Efficiency of Communications in Federated Split Learning
![QR code for arXiv:1603.04416 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)