Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes

ArXi:2603.27936v1 Announce Type: cross Nonlinear Partial Differential Equations (PDEs) are ubiquitous in mathematical physics and engineering. Although Physics-Informed Neural Networks (PINNs) have emerged as a powerful tool for solving PDE problems, they typically struggle to identify multiple distinct solutions, since they are designed to find one solution at a time. To address this limitation, we