NeurIPS 2020

Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks

Meta Review

The paper addresses the problem of post-training calibration in deep nets which has seen a lot of interest in the community lately. The work brings theoretical and practical contributions that are valuable to both researchers and practitioners. The proposed technique may also be useful for other problems besides post-training calibration. I would encourage the authors to try to improve the clarity of the presentation.