Scholarlink

<p>Stochastic differential equations (SDEs) are one of the most commonly studied probabilistic dynamical systems, and widely used to model complex biological processes. Building upon the previously introduced idea of performing inference of dynamical systems by parametrising their coefficient functions via neural networks, we propose a novel formulation for an optimisation objective that combines simulation-based penalties with pseudo-likelihoods. This greatly improves prediction performance compared to the state-of-the-art, and makes it possible to learn a wide variety of dynamics without any prior assumptions on analytical structure.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Loss formulations for assumption-free neural inference of SDE coefficient functions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月1日

查看全文
  • Marc Vaisband,
  • Valentin von Bornhaupt,
  • Nina Schmid,
  • Izdar Abulizi,
  • Jan Hasenauer

摘要

Stochastic differential equations (SDEs) are one of the most commonly studied probabilistic dynamical systems, and widely used to model complex biological processes. Building upon the previously introduced idea of performing inference of dynamical systems by parametrising their coefficient functions via neural networks, we propose a novel formulation for an optimisation objective that combines simulation-based penalties with pseudo-likelihoods. This greatly improves prediction performance compared to the state-of-the-art, and makes it possible to learn a wide variety of dynamics without any prior assumptions on analytical structure.