TPAMI paper unifies Bregman divergences with surrogate losses for learning

FrnkNlsn · x · 2026-07-23

A TPAMI paper by Richard Nock and Frank Nielsen studies Bregman divergences and surrogate losses for learning. The abstract says it connects classification-calibrated surrogates with several common assumptions, derives equivalent forms for convex and non-convex surrogates, and shows shared algorithmic structure across additive regression, logistic loss, and CART-style top-down induction. It also reports experiments on 40 benchmark domains.

Original post →

More from Research

Research channel →