15
3

PAC Verification of Statistical Algorithms

Abstract

Goldwasser et al. (2021) recently proposed the setting of PAC verification, where a hypothesis (machine learning model) that purportedly satisfies the agnostic PAC learning objective is verified using an interactive proof. In this paper we develop this notion further in a number of ways. First, we prove a lower bound of Ω(d/ε2)\Omega\left(\sqrt{d}/\varepsilon^2\right) i.i.d.\ samples for PAC verification of hypothesis classes of VC dimension dd. Second, we present a protocol for PAC verification of unions of intervals over R\mathbb{R} that improves upon their proposed protocol for that task, and matches our lower bound's dependence on dd. Third, we introduce a natural generalization of their definition to verification of general statistical algorithms, which is applicable to a wider variety of settings beyond agnostic PAC learning. Showcasing our proposed definition, our final result is a protocol for the verification of statistical query algorithms that satisfy a combinatorial constraint on their queries.

View on arXiv
Comments on this paper