A Bregman divergence approach yields a unified calibeating framework for general proper losses, delivering U-calibration and logarithmic regret for Tsallis losses with weaker dimension dependence than prior work.
A generalized bias-variance decomposition for
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Calibeating for general proper losses: A Bregman divergence approach
A Bregman divergence approach yields a unified calibeating framework for general proper losses, delivering U-calibration and logarithmic regret for Tsallis losses with weaker dimension dependence than prior work.