pith. sign in

arxiv: 1710.05782 · v1 · pith:IXWOOFPInew · submitted 2017-10-16 · 🧮 math.OC

Second-Order Methods with Cubic Regularization Under Inexact Information

classification 🧮 math.OC
keywords inexactmethodsunderalgorithmsconvergencecubicinformationrate
0
0 comments X
read the original abstract

In this paper, we generalize (accelerated) Newton's method with cubic regularization under inexact second-order information for (strongly) convex optimization problems. Under mild assumptions, we provide global rate of convergence of these methods and show the explicit dependence of the rate of convergence on the problem parameters. While the complexity bounds of our presented algorithms are theoretically worse than those of their exact counterparts, they are at least as good as those of the optimal first-order methods. Our numerical experiments also show that using inexact Hessians can significantly speed up the algorithms in practice.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Decentralized Inexact Cubic Newton Method with Consensus Procedure

    math.OC 2026-05 unverdicted novelty 7.0

    The paper develops decentralized inexact Cubic Newton methods for convex and strongly convex optimization that match centralized iteration complexities with only polylogarithmic extra communication rounds via consensu...

  2. Select-then-differentiate: Solving Bilevel Optimization with Manifold Lower-level Solution Sets

    math.OC 2026-05 unverdicted novelty 7.0

    Optimistic bilevel optimization with manifold lower-level minimizers is differentiable if the optimistic selection is unique, yielding a pseudoinverse hyper-gradient and a convergent HG-MS algorithm whose rate depends...

  3. Decentralized Inexact Cubic Newton Method with Consensus Procedure

    math.OC 2026-05 unverdicted novelty 6.0

    Decentralized Cubic Newton method for convex optimization that matches exact centralized iteration complexity with polylogarithmic extra communication rounds under gradient L1-smoothness and Hessian L2-Lipschitz continuity.