AI RESEARCH
A Theoretical Framework for Statistical Evaluability of Generative Models
arXiv CS.LG
•
ArXi:2604.05324v1 Announce Type: new Statistical evaluation aims to estimate the generalization performance of a model using held-out i.i.d.\ test data sampled from the ground-truth distribution. In supervised learning settings such as classification, performance metrics such as error rate are well-defined, and test error reliably approximates population error given sufficiently large datasets.