On the Curved Geometry of Accelerated
Optimization
Aaron Defazio
Facebook AI Research
New York
Abstract
In this work we propose a differential geometric motivation for Nesterov’s accel-
erated gradient method (AGM) for strongly-convex problems. By considering
the optimization procedure as occurring on a Riemannian manifold with a natural
structure, The AGM method can be seen as ...


雷达卡


京公网安备 11010802022788号







