Poster
in
Workshop: Deep Generative Model in Machine Learning: Theory, Principle and Efficacy （2nd Workshop）

A Complete Decomposition of Stochastic Differential Equations

Samuel Duffield

Project Page [ OpenReview]

Abstract

We show that any stochastic differential equation with prescribed time-dependent marginal distributions admits a decomposition into three components: a unique scalar field governing marginal evolution, a symmetric positive-semidefinite diffusion matrix field and a skew-symmetric matrix field.

Chat is not available.