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 1005.3014math.LOcs.LOmath.PRmath.STstat.MLstat.TH
收藏

关于条件概率的可计算性

On the computability of conditional probability

Nathanael L. Ackerman, Cameron E. Freer, Daniel M. Roy

摘要:

随着计算机科学中的归纳推理和机器学习方法不断取得成功,研究人员的目标是描述更复杂的概率模型和推理算法。人们自然会问,概率推理是否存在一种通用的计算程序。我们研究条件概率的可计算性,条件概率是概率论中的一个基本概念,也是贝叶斯统计的基石。我们表明,有可计算的联合分布与不可计算的条件分布,排除了一般的推理算法的前景,甚至效率低下的。具体来说,我们构造一对可计算的随机变量在单位区间,使条件分布的第一个变量的第二个编码的停机问题。然而,概率推理是可能的,在许多常见的建模设置,我们证明了几个结果,给出了广泛适用的条件下,条件分布是可计算的。特别是,条件分布成为可计算的测量时,被破坏的独立的可计算的噪声与足够光滑的有界密度。

英文摘要:

As inductive inference and machine learning methods in computer science see continued success, researchers are aiming to describe ever more complex probabilistic models and inference algorithms. It is natural to ask whether there is a universal computational procedure for probabilistic inference. We investigate the computability of conditional probability, a fundamental notion in probability theory and a cornerstone of Bayesian statistics. We show that there are computable joint distributions with noncomputable conditional distributions, ruling out the prospect of general inference algorithms, even inefficient ones. Specifically, we construct a pair of computable random variables in the unit interval such that the conditional distribution of the first variable given the second encodes the halting problem. Nevertheless, probabilistic inference is possible in many common modeling settings, and we prove several results giving broadly applicable conditions under which conditional distributions are computable. In particular, conditional distributions become computable when measurements are corrupted by independent computable noise with a sufficiently smooth bounded density.

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。

↑