Bias-Variance Decompositions for Margin Losses

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


We introduce a novel bias-variance decomposition for a range of strictly convex margin losses, including the logistic loss (minimized by the classic LogitBoost algorithm), as well as the squared margin loss and canonical boosting loss. Furthermore, we show that, for all strictly convex margin losses, the expected risk decomposes into the risk of a “central” model and a term quantifying variation in the functional margin with respect to variations in the training data. These decompositions provide a diagnostic tool for practitioners to understand model overfitting/underfitting, and have implications for additive ensemble models—for example, when our bias-variance decomposition holds, there is a corresponding “ambiguity” decomposition, which can be used to quantify model diversity.
Original languageEnglish
Title of host publicationProceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022,
Publication statusPublished - 29 Mar 2022


Dive into the research topics of 'Bias-Variance Decompositions for Margin Losses'. Together they form a unique fingerprint.

Cite this