AI RESEARCH
Local Inverse Geometry Can Be Amortized
arXiv CS.LG
•
ArXi:2605.13068v1 Announce Type: new Nonlinear inverse problems often trade inexpensive but fragile first-order updates against curvature-aware methods such as Gauss-Newton and Levenberg-Marquardt, which obtain stronger directions by repeatedly solving Jacobian-based linearized systems. We propose a learned alternative: amortize local inverse geometry into a reusable reverse operator.