A Bregman divergence approach yields a general calibeating framework that achieves U-calibration with logarithmic regret for Tsallis losses and a new regret equality for Be The Regularized Leader.
A generalized bias-variance decomposition for Bregman divergences
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Extends UMVUE theory to Bregman losses by introducing dual-space unbiasedness and proving Rao-Blackwell and Lehmann-Scheffé analogs for type-I Bregman UMVUEs.
CART impurity criteria are reframed as Bregman divergences from convex functions, unifying node representatives, split rules, and consistency results for exponential-family models.
citing papers explorer
-
Calibeating for general proper losses: A Bregman divergence approach
A Bregman divergence approach yields a general calibeating framework that achieves U-calibration with logarithmic regret for Tsallis losses and a new regret equality for Be The Regularized Leader.
-
UMVUE-Type Estimators under Bregman Losses
Extends UMVUE theory to Bregman losses by introducing dual-space unbiasedness and proving Rao-Blackwell and Lehmann-Scheffé analogs for type-I Bregman UMVUEs.
-
A Bregman Perspective on Classification and Regression Trees
CART impurity criteria are reframed as Bregman divergences from convex functions, unifying node representatives, split rules, and consistency results for exponential-family models.