Skip to content

An Optimal Agnostic PAC Algorithm

Markus Engelund Mathiasen, Jian Qian, Nikita Zhivotovskiy

cs.LGarXiv:2608.06363

Abstract

Let H⊂eq\-1,+1\X be a class of finite VC dimension d1. Writing L for the binary risk and L*=h∈ HL(h), we construct a learner achieving the statistically optimal risk bound: from an i.i.d.\ sample of size n, for every 0<δ 1/2, with probability at least 1-δ, \[ L( h) L*+ 7·108( L*(d+(1/δ))n +d+(1/δ)n ). \] This settles the sample complexity of agnostic PAC learning up to universal constants at every fixed L*, matching the lower bounds of Devroye, Györfi, and Lugosi [A Probabilistic Theory of Pattern Recognition, Springer, 1996].

Create a lesson