Technology & AIAug 21, 2026
Primal Acceleration of Newton's Method
We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian.
We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. The algorithm uses only primal variables and performs just one linear solve per iteration. With a simple predetermined choice of parameters, it achieves the…
Sign in to learn & save →
The frontier is open to all. Sign in to learn this from first principles and save it to your knowledge base.