arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1810.00481quant-phcs.CCcs.LG
收藏

关于量子精确学习的两个新结果

Two new results about quantum exact learning

IBM T. J. Watson Research Center(IBM T. J. 沃森研究中心);Center for Theoretical Physics, MIT(麻省理工学院);QuSoft, CWI(荷兰国家数学与计算机科学研究中心);Indian Statistical Institute(印度统计研究所);Centre for Quantum Software and Information, University of Technology Sydney(悉尼科技大学);School for Physical and Mathematical Sciences, Nanyang Technological University(南洋理工大学);Centre for Quantum Technologies, Singapore(新加坡国立大学量子科技中心);QuSoft, CWI and University of Amsterdam(阿姆斯特丹大学)

Srinivasan Arunachalam, Sourav Chakraborty, Troy Lee, Manaswi Paraashar, Ronald de Wolf

摘要:

我们提出了量子计算机精确学习的两个新结果。首先,我们展示了如何从该函数的$O(k^{1.5}(\log k)^2)$均匀量子示例中准确地学习$k$ -傅立叶稀疏$n$ -位布尔函数。这改进了$\widetildeΘ(kn)$均匀随机\emph{classical}示例的界限(Haviv和Regev,CCC'15)。此外,我们提供了一个可能的方向,以提高我们的$\widetilde{O}(k^{1.5})$上界证明了改进的张引理$k$ -傅立叶稀疏布尔函数。其次,我们表明,如果一个概念类$\mathcal{C}$可以完全学习使用$Q$量子成员查询,那么它也可以学习使用$O\left(\frac{Q^2}{\log Q}\log|\mathcal{C}|\right)$ \emph{classical}成员查询。这通过$\log Q$因子改进了先前最佳模拟结果(Servedio和Gortler,SICOMP'04)。

英文摘要:

We present two new results about exact learning by quantum computers. First, we show how to exactly learn a $k$-Fourier-sparse $n$-bit Boolean function from $O(k^{1.5}(\log k)^2)$ uniform quantum examples for that function. This improves over the bound of $\widetildeΘ(kn)$ uniformly random \emph{classical} examples (Haviv and Regev, CCC'15). Additionally, we provide a possible direction to improve our $\widetilde{O}(k^{1.5})$ upper bound by proving an improvement of Chang's lemma for $k$-Fourier-sparse Boolean functions. Second, we show that if a concept class $\mathcal{C}$ can be exactly learned using $Q$ quantum membership queries, then it can also be learned using $O\left(\frac{Q^2}{\log Q}\log|\mathcal{C}|\right)$ \emph{classical} membership queries. This improves the previous-best simulation result (Servedio and Gortler, SICOMP'04) by a $\log Q$-factor.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑