Sep 30, 2018 · We consider a variant of inexact Newton Method, called Newton-MR, in which the least-squares sub-problems are solved approximately using Minimum ...

Newton-MR: Theory. Newton-MR: Experiments. Newton-MR: Newton's Method Without. Smoothness or Convexity. Michael W. Mahoney. ICSI and Department of Statistics.

In this thesis, we consider variants of inexact Newton Method [1, 2], called Newton-MR, in which the symmetric least-squares sub-problems are solved using ...

We introduce and study the damped regularized Newton's method (DRNM). It converges globally for any strictly convex function, which has a minimizer in $R^n$.

A Newton-CG algorithm with complexity guarantees for smooth unconstrained optimization · Mathematics, Computer Science. Mathematical Programming · 2019. We ...

Establishing global convergence of the classical Newton's method has long been limited to making (strong) convexity assumptions.

When f is smooth and strongly convex, it is well known that the local and global convergence rates of the classical Newton's method are, respectively, quadratic ...

Sep 17, 2019 · We show that two simple modifications of the classical Newton's method result in an algorithm, called Newton-MR, which is almost ...

Missing: Newton's | Show results with:Newton's

Bibliographic details on Newton-MR: Newton's Method Without Smoothness or Convexity.