#machine learning
Sep 2026
lapanda: A Matrix-Free Differentiable Solver for Nonconvex Constrained Optimization Layers
This work reformulates the problem to a sequence of augmented Lagrangian subproblems, each handled by a first-order inner solver through a proximal averaged quasi-Newton algorithm with adaptive linesearch, thus enabling efficient forward optimization.
Yuan-Kun Chen, Zi-Fei Nie, Kang-Yu Lin et al.
· arXiv.org · 0 citations