Milstein-driven neural stochastic differential equation model with uncertainty estimates

Xiao Zhang, Wei Wei, Zhen Zhang, Lei Zhang, Wei Li

Research output: Contribution to journalArticlepeer-review

4 Scopus citations

Abstract

Incorporating uncertainty quantification into the modeling of deep learning-based model has become a research focus in the deep learning community. Within this group of methods, stochastic differential equation (SDE)-based models have demonstrated advantages in their ability to model uncertainty quantification. However, the use of Euler's method in these models introduces imprecise numerical solutions, which limits the accuracy of SDE systems and weakens the performance of the network. In this study, we build a more precise Milstein-driven SDE network (MDSDE-Net) to improve the network performance. In addition, we analyze the convergence of the Milstein scheme and theoretically guarantee the feasibility of MDSDE-Net. Experimental and theoretical results show that the MDSDE-Net outperforms existing models.

Original languageEnglish
Pages (from-to)71-77
Number of pages7
JournalPattern Recognition Letters
Volume174
DOIs
StatePublished - Oct 2023

Keywords

  • Milstein-driven SDE-net
  • Stochastic differential equation
  • Uncertainty quantification

Fingerprint

Dive into the research topics of 'Milstein-driven neural stochastic differential equation model with uncertainty estimates'. Together they form a unique fingerprint.

Cite this