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 1304.4633cs.DScs.LGcs.LO
收藏

限制分布上归结的PAC拟自动化

PAC Quasi-automatizability of Resolution over Restricted Distributions

Harvard University(哈佛大学)

Brendan Juba

摘要:

我们认为原则性的替代方案,无监督学习在数据采掘的情况下,学习任务的后续分析任务。具体地说,我们考虑一个问答(假设检验)任务:在组合任务中,我们通过直接使用输入示例来判断输入查询公式在背景分布上是否满足,而不是调用两阶段过程,其中(i)通过无监督学习算法学习关于分布的规则,以及(ii)推理算法决定查询公式是否遵循所学习的规则。在之前的工作(2013)中,我们观察到学习任务可以满足这种组合环境中的许多理想标准-有效地匹配通过从部分信息中对CNF进行不可知学习所能实现的目标-这些目标是无法直接实现的。在这项工作中,我们表明,同样,有推理任务是可以实现的,在这样一个组合的背景下,不知道是可以直接实现的(事实上,已经严重警告是不可能的,参见。(Alekhnovich和Razborov,2008))。也就是说,我们测试一个决议证明的查询公式的一个给定的大小在quasipolynomial时间(即“准自动化”决议)。我们考虑的学习设置是一个部分信息,限制分布设置,它从部分信息中概括了均匀分布上的学习奇偶性,这是另一个已知在各种模型中无法直接实现的任务(参见。(Ben-David和Dichterman,1998)和(Michael,2010))。

英文摘要:

We consider principled alternatives to unsupervised learning in data mining by situating the learning task in the context of the subsequent analysis task. Specifically, we consider a query-answering (hypothesis-testing) task: In the combined task, we decide whether an input query formula is satisfied over a background distribution by using input examples directly, rather than invoking a two-stage process in which (i) rules over the distribution are learned by an unsupervised learning algorithm and (ii) a reasoning algorithm decides whether or not the query formula follows from the learned rules. In a previous work (2013), we observed that the learning task could satisfy numerous desirable criteria in this combined context -- effectively matching what could be achieved by agnostic learning of CNFs from partial information -- that are not known to be achievable directly. In this work, we show that likewise, there are reasoning tasks that are achievable in such a combined context that are not known to be achievable directly (and indeed, have been seriously conjectured to be impossible, cf. (Alekhnovich and Razborov, 2008)). Namely, we test for a resolution proof of the query formula of a given size in quasipolynomial time (that is, "quasi-automatizing" resolution). The learning setting we consider is a partial-information, restricted-distribution setting that generalizes learning parities over the uniform distribution from partial information, another task that is known not to be achievable directly in various models (cf. (Ben-David and Dichterman, 1998) and (Michael, 2010)).

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。

↑