arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1311.6591cs.AI
收藏

提升推理中二元证据的复杂性与近似性

On the Complexity and Approximation of Binary Evidence in Lifted Inference

University of California, Los Angeles(加州大学洛杉矶分校)

Guy Van den Broeck, Adnan Darwiche

摘要:

提升推理算法利用概率模型中的对称性来加速推理。它们在计算关系模型中的无条件概率时表现出令人印象深刻的性能,但在计算条件概率时经常采用非提升推理。原因是,对证据的条件化破坏了模型的许多对称性,这可能会抢占标准提升技术。最近的理论结果表明,例如,条件的证据,对应于二元关系是P-硬,这表明没有提升是预期在最坏的情况下。在本文中,我们平衡这个负面的结果,通过确定布尔等级的证据作为一个关键参数,用于表征的复杂性条件提升推理。特别是,我们表明,条件与有界布尔秩的二元证据是有效的。这开辟了一个低秩布尔矩阵分解,我们从理论和经验上研究近似证据的可能性。

英文摘要:

Lifted inference algorithms exploit symmetries in probabilistic models to speed up inference. They show impressive performance when calculating unconditional probabilities in relational models, but often resort to non-lifted inference when computing conditional probabilities. The reason is that conditioning on evidence breaks many of the model's symmetries, which can preempt standard lifting techniques. Recent theoretical results show, for example, that conditioning on evidence which corresponds to binary relations is #P-hard, suggesting that no lifting is to be expected in the worst case. In this paper, we balance this negative result by identifying the Boolean rank of the evidence as a key parameter for characterizing the complexity of conditioning in lifted inference. In particular, we show that conditioning on binary evidence with bounded Boolean rank is efficient. This opens up the possibility of approximating evidence by a low-rank Boolean matrix factorization, which we investigate both theoretically and empirically.

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。

↑