Crandore Hub

mcboost

Multi-Calibration Boosting

Implements 'Multi-Calibration Boosting' (2018) <https://proceedings.mlr.press/v80/hebert-johnson18a.html> and 'Multi-Accuracy Boosting' (2019) <doi:10.48550/arXiv.1805.12317> for the multi-calibration of a machine learning model's prediction. 'MCBoost' updates predictions for sub-groups in an iterative fashion in order to mitigate biases like poor calibration or large accuracy differences across subgroups. Multi-Calibration works best in scenarios where the underlying data & labels are unbiased, but resulting models are. This is often the case, e.g. when an algorithm fits a majority population while ignoring or under-fitting minority populations.

Versions across snapshots

VersionRepositoryFileSize
0.4.4 rolling linux/jammy R-4.5 mcboost_0.4.4.tar.gz 380.7 KiB
0.4.4 rolling linux/noble R-4.5 mcboost_0.4.4.tar.gz 380.7 KiB
0.4.4 rolling source/ R- mcboost_0.4.4.tar.gz 72.3 KiB
0.4.4 latest linux/jammy R-4.5 mcboost_0.4.4.tar.gz 380.7 KiB
0.4.4 latest linux/noble R-4.5 mcboost_0.4.4.tar.gz 380.7 KiB
0.4.4 latest source/ R- mcboost_0.4.4.tar.gz 72.3 KiB
0.4.4 2026-04-26 source/ R- mcboost_0.4.4.tar.gz 72.3 KiB
0.4.4 2026-04-23 source/ R- mcboost_0.4.4.tar.gz 72.3 KiB
0.4.4 2026-04-09 windows/windows R-4.5 mcboost_0.4.4.zip 389.5 KiB
0.4.3 2025-04-20 source/ R- mcboost_0.4.3.tar.gz 74.8 KiB

Dependencies (latest)

Imports

Suggests