arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.04342cs.ITcs.DMmath.ITmath.STstat.TH
收藏

从池化数据的近最优有效解码

Near optimal efficient decoding from pooled data

Max Hahn-Klimroth, Noela Müller

摘要:

考虑$n$项目,每个项目都由$\{0, \ldots, d\}$中的一个$d+1$可能特征表征。我们研究的推理任务学习这些类型的查询子集,或池,只揭示了一种形式的粗化信息的功能-在我们的情况下,池中的所有功能的总和的项目。在数据汇集过程中存在内存或技术限制的情况下,或者在数据需要匿名的情况下,这是一个现实的场景。相关的突出问题是定量组测试问题,它是一个概括,以及压缩感知问题,它是一个特殊的情况。在本文中,我们感兴趣的是有效地推断标签所需的最小数量的查询,如果其中一个功能,比如$0$,是占主导地位的,在这个意义上,项目中的非零功能的数量$k$比$n$小得多。已知在这种情况下,通过使用不超过$O(k)$查询,可以在指数时间内恢复所有特征。然而,到目前为止,所有的\textit{efficient}推理算法都至少需要$Ω(k\ln n)$查询,并且不知道这个差距是人为的还是根本性的。在这里,我们表明,事实上,以前的差距之间的信息理论和计算界限是不是固有的问题,通过提供一个有效的算法,成功的概率很高,并采用不超过$O(k)$测量。这也解决了一个长期悬而未决的问题,定量组测试的问题。

英文摘要:

Consider $n$ items, each of which is characterised by one of $d+1$ possible features in $\{0, \ldots, d\}$. We study the inference task of learning these types by queries on subsets, or pools, of the items that only reveal a form of coarsened information on the features - in our case, the sum of all the features in the pool. This is a realistic scenario in situations where one has memory or technical constraints in the data collection process, or where the data is subject to anonymisation. Related prominent problems are the quantitative group testing problem, of which it is a generalisation, as well as the compressed sensing problem, of which it is a special case. In the present article, we are interested in the minimum number of queries needed to efficiently infer the labels, if one of the features, say $0$, is dominant in the sense that the number $k$ of non-zero features among the items is much smaller than $n$. It is known that in this case, all features can be recovered in exponential time by using no more than $O(k)$ queries. However, so far, all \textit{efficient} inference algorithms required at least $Ω(k\ln n)$ queries, and it was unknown whether this gap is artificial or of a fundamental nature. Here we show that indeed, the previous gap between the information-theoretic and computational bounds is not inherent to the problem by providing an efficient algorithm that succeeds with high probability and employs no more than $O(k)$ measurements. This also solves a long standing open question for the quantitative group testing problem.

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。

↑