Two-Step MV-DeepONet: Probabilistic Operator Learning for Uncertainty Propagation Driven by Random Input Fields 文章

ArXiv CS.AI2026-08-11PAPERen作者: Yupei Nie, Lei Wang, Jiasen Liu

详细信息

来源站点
ArXiv CS.AI
作者
Yupei Nie, Lei Wang, Jiasen Liu
文章类型
PAPER
语言
en
发布日期
2026-08-11

摘要

arXiv:2608.09071v1 Announce Type: cross Abstract: Forward uncertainty propagation in complex physical systems can induce structured covariance across field-valued outputs. For a probabilistic surrogate, the total predictive covariance comprises the covariance of conditional means across input realizations and the average conditional predictive covariance. Probabilistic DeepONet (Prob-DeepONet) provides lightweight uncertainty quantification by predicting pointwise Gaussian means and variances in a single forward pass, but its conditional predictive covariance is restricted to a diagonal form. To represent cross-location conditional dependence without explicitly parameterizing a full high-dimensional covariance matrix, we develop a two-step mean-variance DeepONet (two-step MV-DeepONet) through two principal modifications. First, two-step training is used to decouple output-basis learning from the input-to-coefficient mapping, together with basis orthogonalization and subspace rotation.