AI RESEARCH
Layerwise LQR for Geometry-Aware Optimization of Deep Networks
arXiv CS.AI
•
ArXi:2605.04230v1 Announce Type: cross Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners usually impose structural approximations early, often discarding cross-layer interactions induced by the network computation. We