AI RESEARCH
Realizable Bayes-Consistency for General Metric Losses
arXiv CS.LG
•
ArXi:2605.03823v1 Announce Type: new We study strong universal Bayes-consistency in the realizable setting for learning with general metric losses, extending classical characterizations beyond $0$-$1$ classification \citep{bousquet_theory_2021, hanneke2021universalbayesconsistencymetric} and real-valued regression \citep{attias_universal_2024