Zhipeng Chang

Unsupervised Operator Learning Approach for Dissipative Equations via Onsager Principle

The deep Onsager operator learning (DOOL) method is proposed, a novel unsupervised framework for solving dissipative equations Rooted in the Onsager variational principle, DOOL trains a deep operator network by directly minimizing the OVP-defined Rayleighian functional, requiring no labeled data, and then proceeds in t...