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 1809.00901cs.ITcs.HCcs.LGmath.IT
收藏

二元分类的奇偶校验

Parity Queries for Binary Classification

KAIST(韩国科学技术院);University of Michigan(密歇根大学)

Hye Won Chung, Ji Oon Lee, Doyeon Kim, Alfred O. Hero

摘要:

考虑一个基于查询的数据采集问题,其目的是从所选变量子集的奇偶校验(XOR)测量中恢复$k$二进制变量的值。假设响应模型,其中仅接收随机选择的测量子集。我们提出了一种方法,用于设计一个序列的查询,使变量可以被识别的概率高,使用尽可能少的($n$)测量。我们将查询难度$\bar{d}$定义为查询子集的平均大小,将样本复杂度$n$定义为达到给定恢复精度所需的最小测量次数。我们得到恢复精度,查询难度和样本复杂性之间的基本权衡。特别地,以高概率恢复所有$k$变量所需的必要且充分的样本复杂度是$n = c_0 \max\{k, (k \log k)/\bar{d}\}$,并且恢复$δ=o(1)$的变量的固定比例$(1-δ)k$的样本复杂度是$n = c_1\max\{k, (k \log(1/δ))/\bar{d}\}$,其中$c_0, c_1>0$。

英文摘要:

Consider a query-based data acquisition problem that aims to recover the values of $k$ binary variables from parity (XOR) measurements of chosen subsets of the variables. Assume the response model where only a randomly selected subset of the measurements is received. We propose a method for designing a sequence of queries so that the variables can be identified with high probability using as few ($n$) measurements as possible. We define the query difficulty $\bar{d}$ as the average size of the query subsets and the sample complexity $n$ as the minimum number of measurements required to attain a given recovery accuracy. We obtain fundamental trade-offs between recovery accuracy, query difficulty, and sample complexity. In particular, the necessary and sufficient sample complexity required for recovering all $k$ variables with high probability is $n = c_0 \max\{k, (k \log k)/\bar{d}\}$ and the sample complexity for recovering a fixed proportion $(1-δ)k$ of the variables for $δ=o(1)$ is $n = c_1\max\{k, (k \log(1/δ))/\bar{d}\}$, where $c_0, c_1>0$.

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。

↑