期刊
INFORMATION PROCESSING LETTERS
卷 111, 期 1, 页码 40-45出版社
ELSEVIER
DOI: 10.1016/j.ipl.2010.10.007
关键词
PAC (Probably Approximately Correct); learning; Lower bound; Quantum algorithm; VC dimension; Computational complexity
资金
- National Science Foundation
- Direct For Computer & Info Scie & Enginr
- Division of Computing and Communication Foundations [0829537] Funding Source: National Science Foundation
In this paper, we study the quantum PAC learning model, offering an improved lower bound on the query complexity. For a concept class with VC dimension d, the lower bound is Omega(1/epsilon(d(1-e) + log(1/delta))) for epsilon accuracy and 1 - delta confidence, where e can be an arbitrarily small positive number. The lower bound is very close to the best lower bound known on query complexity for the classical PAC learning model, which is Omega(1/epsilon(d + log(1/delta))) (c) 2010 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据