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 1901.06540cs.LOcs.PL
收藏

概率灵敏度的预期望演算

A Pre-Expectation Calculus for Probabilistic Sensitivity

Alejandro Aguirre, Gilles Barthe, Justin Hsu, Benjamin Lucien Kaminski, Joost-Pieter Katoen, Christoph Matheja

摘要:

灵敏度属性描述了程序输入的变化如何影响输出,通常是通过对应输入之间距离的单调函数来上界两次运行的输出之间的距离。当程序是概率性的时,输出之间的距离就是分布之间的距离。康托洛维奇提升提供了一种通过提升底层样本空间的距离来定义分布之间距离的一般方法;通过在基空间上选择适当的距离,可以恢复其他常见的概率距离,例如全变差距离。我们开发了一个关系的预期望演算的概率程序的两次执行之间的Kantorovich距离的上限。我们通过证明机器学习算法的算法稳定性、强化学习算法的收敛性以及洗牌算法的快速混合来说明我们的方法。我们还考虑了一些扩展:证明总变差距离的下界和收敛到均匀分布。最后,我们描述了一个异步扩展我们的演算的原因对程序执行不同的控制流。

英文摘要:

Sensitivity properties describe how changes to the input of a program affect the output, typically by upper bounding the distance between the outputs of two runs by a monotone function of the distance between the corresponding inputs. When programs are probabilistic, the distance between outputs is a distance between distributions. The Kantorovich lifting provides a general way of defining a distance between distributions by lifting the distance of the underlying sample space; by choosing an appropriate distance on the base space, one can recover other usual probabilistic distances, such as the Total Variation distance. We develop a relational pre-expectation calculus to upper bound the Kantorovich distance between two executions of a probabilistic program. We illustrate our methods by proving algorithmic stability of a machine learning algorithm, convergence of a reinforcement learning algorithm, and fast mixing for card shuffling algorithms. We also consider some extensions: proving lower bounds on the Total Variation distance and convergence to the uniform distribution. Finally, we describe an asynchronous extension of our calculus to reason about pairs of program executions with different control flow.

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。

↑