No AI summary available for this article.
Why It Matters
We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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 global convergence rate of $O(1/k^3)$ in terms of the functional residual. To the best of our knowledge, this is the first second-order method for this problem class attaining this rate while relying solely on one linear system solve per iteration (without solving auxiliary nonlinear regularized subproblems, such as cubic re...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.21359v1 · Indexed 7 days ago