Subspace Uncertainty and Sharp Sampling Thresholds on the Boolean Cube

2026-10-09来源 arXiv math.ITEnglish
arXiv:2610.12358v1 Announce Type: cross Abstract: We study Gaussian regression under squared population $L_2$ loss in a known $m$-dimensional subspace of degree-at-most-$k$ functions on the $d$-dimensional Boolean cube. Random inputs can undersample regions essential for prediction, delaying the parametric rate even when the model is known. For fixed $q_0

原文：https://www.a8q9.cn/en/article/subspace-uncertainty-and-sharp-sampling-thresholds-on-the-boolean-cube-28f51b.html

相关文章