Proper Agnostic Learning of Affine Halfspaces under Log-Concave Marginals
arXiv:2611.04344v1 Announce Type: cross Abstract: We give a proper constant-factor agnostic learner for affine halfspaces under full-dimensional log-concave marginals. For arbitrary binary labels, the algorithm uses independent labeled samples and returns a single affine halfspace with error at mos…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv stat.ML
Proper Agnostic Learning of Affine Halfspaces under Log-Concave Marginals