Computational and Statistical Asymptotic Analysis of the JKO Scheme for Iterative Algorithms to update distributions

TL;DR

This paper extends the JKO scheme for distribution computation to models with unknown parameters, developing statistical estimation methods and analyzing their asymptotic behavior through stochastic PDEs, with applications in machine learning.

Contribution

It introduces a unified framework for joint computational and statistical asymptotic analysis of the extended JKO scheme with unknown parameters.

Findings

Asymptotic theory via stochastic PDEs describes the scheme's limiting behavior.

Numerical simulations validate the finite-sample performance and theoretical results.

Abstract

The seminal paper of Jordan, Kinderlehrer, and Otto introduced what is now widely known as the JKO scheme, an iterative algorithmic framework for computing distributions. This scheme can be interpreted as a Wasserstein gradient flow and has been successfully applied in machine learning contexts, such as deriving policy solutions in reinforcement learning. In this paper, we extend the JKO scheme to accommodate models with unknown parameters. Specifically, we develop statistical methods to estimate these parameters and adapt the JKO scheme to incorporate the estimated values. To analyze the adopted statistical JKO scheme, we establish an asymptotic theory via stochastic partial differential equations that describes its limiting dynamic behavior. Our framework allows both the sample size used in parameter estimation and the number of algorithmic iterations to go to infinity. This study offers a unified framework for joint computational and statistical asymptotic analysis of the statistical JKO scheme. On the computational side, we examine the scheme's dynamic behavior as the number of iterations increases, while on the statistical side, we investigate the large-sample behavior of the resulting distributions computed through the scheme. We conduct numerical simulations to evaluate the finite-sample performance of the proposed methods and validate the developed asymptotic theory.