DeepAI AI Chat
Log In Sign Up

A Newton-CG based barrier method for finding a second-order stationary point of nonconvex conic optimization with complexity guarantees

07/12/2022
by   Chuan He, et al.
University of Minnesota
0

In this paper we consider finding an approximate second-order stationary point (SOSP) of nonconvex conic optimization that minimizes a twice differentiable function over the intersection of an affine subspace and a convex cone. In particular, we propose a Newton-conjugate gradient (Newton-CG) based barrier method for finding an (ϵ,√(ϵ))-SOSP of this problem. Our method is not only implementable, but also achieves an iteration complexity of O(ϵ^-3/2), which matches the best known iteration complexity of second-order methods for finding an (ϵ,√(ϵ))-SOSP of unconstrained nonconvex optimization. The operation complexity of O(ϵ^-3/2min{n,ϵ^-1/4}), measured by the amount of fundamental operations, is also established for our method.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/10/2023

A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization

In this paper we consider finding an approximate second-order stationary...
05/30/2015

Saddle-free Hessian-free Optimization

Nonconvex optimization problems such as the ones in training deep neural...
07/01/2018

A polynomial time log barrier method for problems with nonconvex constraints

Interior point methods (IPMs) that handle nonconvex constraints such as ...
07/31/2019

Multi-Point Bandit Algorithms for Nonstationary Online Nonconvex Optimization

Bandit algorithms have been predominantly analyzed in the convex setting...
05/22/2018

Cutting plane methods can be extended into nonconvex optimization

We show that it is possible to obtain an O(ϵ^-4/3) runtime --- including...
02/10/2020

On Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions

We provide the first non-asymptotic analysis for finding stationary poin...