A Pre-Expectation Calculus for Probabilistic Sensitivity

TL;DR

This paper introduces a relational pre-expectation calculus to upper bound the Kantorovich distance between probabilistic program executions, aiding in analyzing stability, convergence, and mixing properties.

Contribution

It develops a novel calculus for probabilistic sensitivity analysis, extending to lower bounds and asynchronous reasoning, with applications in machine learning and algorithms.

Findings

Proved algorithmic stability of a machine learning algorithm.

Established convergence of a reinforcement learning algorithm.

Demonstrated fast mixing for card shuffling algorithms.

Abstract

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.