AI RESEARCH
Time-Dependent PDE-Constrained Optimization via Weak-Form Latent Dynamics
arXiv CS.LG
•
ArXi:2605.20639v1 Announce Type: cross Optimization problems constrained by high-dimensional, time-dependent partial differential equations require repeated forward and sensitivity solves, making high-fidelity optimization computationally prohibitive in many-query design and control settings. We present a weak-form latent-space reduced-order modeling framework for accelerating gradient-based PDE-constrained optimization.