A formal proof of PAC learnability for decision stumps
A formal proof of PAC learnability for decision stumps
复制标题
决策树桩的 PAC 可学习性的正式证明
DOI:
10.1145/3437992.3439917
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
Jean
中科院分区:
文献类型:
--
作者:
Joseph Tassarotti;Koundinya Vajjha;Anindya Banerjee;Jean
We present a formal proof in Lean of probably approximately correct (PAC) learnability of the concept class of decision stumps. This classic result in machine learning theory derives a bound on error probabilities for a simple type of classifier. Though such a proof appears simple on paper, analytic and measure-theoretic subtleties arise when carrying it out fully formally. Our proof is structured so as to separate reasoning about deterministic properties of a learning function from proofs of measurability and analysis of probabilities.
DOI:
10.1007/s10817-017-9404-x
发表时间:
2017
期刊:
Journal of Automated Reasoning
影响因子:
--
作者:
Jeremy Avigad;Johannes Hölzl;Luke Serafin
通讯作者:
Luke Serafin
DOI:
10.1609/aaai.v33i01.33012662
发表时间:
2019-07
期刊:
ArXiv
影响因子:
--
作者:
Alexander Bagnall;Gordon Stewart
通讯作者:
Alexander Bagnall;Gordon Stewart
DOI:
10.1007/978-3-642-22863-6_12
发表时间:
2011
期刊:
影响因子:
--
作者:
Johannes Hölzl;Armin Heller
通讯作者:
Armin Heller