This paper introduces a novel concept class that demonstrates null measurability at the symmetrization interface in VC learning. The research shows that the requirement for Borel measurability of ghost-gap suprema, previously established in statistical learning theory, is more stringent than necessary. By constructing a specific concept class, the authors prove that certain AI
Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →
arXiv:2604.25028v1 Announce Type: cross Abstract: Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that, at the one-sided ghost-gap interface actually used by the standard symmetrizat…
Recent work revisiting measurability in the fundamental theorem of statistical learning imposes Borel measurability of ghost-gap suprema. We show that, at the one-sided ghost-gap interface actually used by the standard symmetrization proof, this requirement is stronger than neces…