子立方体条件下Junta分布的学习与检验
Learning and Testing Junta Distributions with Subcube Conditioning
摘要:
本文研究了均匀分布下$\{-1,1\}^n$上Junta分布的学习和检验问题,其中一个分布$p$是$k$ -Junta,如果它的概率质量函数$p(x)$依赖于至多$k$变量的子集.主要贡献是一个算法,找到相关的坐标在一个$k$ -junta分布与子立方体条件[BC 18,CCKLW 20]。我们给出两个应用:1.一个学习带有$\tilde{O}(k/ε^2) \log n + O(2^k/ε^2)$子立方体条件查询的$k$ -junta分布的算法; 2.用$\tilde{O}((k + \sqrt{n})/ε^2)$子立方体条件查询检验$k$ -Junta分布的算法。我们所有的算法是最佳的多对数因子。我们的研究结果表明,子立方体条件,作为一个自然的模型访问高维分布,使学习和测试军分布相比,标准的抽样模型显着节省。这解决了Aliakbarpour、Blais和Rubinfeld提出的一个未决问题[ABR 17]。
英文摘要:
We study the problems of learning and testing junta distributions on $\{-1,1\}^n$ with respect to the uniform distribution, where a distribution $p$ is a $k$-junta if its probability mass function $p(x)$ depends on a subset of at most $k$ variables. The main contribution is an algorithm for finding relevant coordinates in a $k$-junta distribution with subcube conditioning [BC18, CCKLW20]. We give two applications: 1. An algorithm for learning $k$-junta distributions with $\tilde{O}(k/ε^2) \log n + O(2^k/ε^2)$ subcube conditioning queries, and 2. An algorithm for testing $k$-junta distributions with $\tilde{O}((k + \sqrt{n})/ε^2)$ subcube conditioning queries. All our algorithms are optimal up to poly-logarithmic factors. Our results show that subcube conditioning, as a natural model for accessing high-dimensional distributions, enables significant savings in learning and testing junta distributions compared to the standard sampling model. This addresses an open question posed by Aliakbarpour, Blais, and Rubinfeld [ABR17].
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。