Cubic Regularization with Momentum for Nonconvex Optimization

10/09/2018
by   Zhe Wang, et al.
4

Momentum is a popular technique to accelerate the convergence in practical training, and its impact on convergence guarantee has been well-studied for first-order algorithms. However, such a successful acceleration technique has not yet been proposed for second-order algorithms in nonconvex optimization.In this paper, we apply the momentum scheme to cubic regularized (CR) Newton's method and explore the potential for acceleration. Our numerical experiments on various nonconvex optimization problems demonstrate that the momentum scheme can substantially facilitate the convergence of cubic regularization, and perform even better than the Nesterov's acceleration scheme for CR. Theoretically, we prove that CR under momentum achieves the best possible convergence rate to a second-order stationary point for nonconvex optimization. Moreover, we study the proposed algorithm for solving problems satisfying an error bound condition and establish a local quadratic convergence rate. Then, particularly for finite-sum problems, we show that the proposed algorithm can allow computational inexactness that reduces the overall sample complexity without degrading the convergence rate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/20/2018

Sample Complexity of Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization

The popular cubic regularization (CR) method converges with first- and s...
research
08/22/2018

A Note on Inexact Condition for Cubic Regularized Newton's Method

This note considers the inexact cubic-regularized Newton's method (CR), ...
research
08/29/2023

Second-order methods for quartically-regularised cubic polynomials, with applications to high-order tensor methods

There has been growing interest in high-order tensor methods for nonconv...
research
05/17/2018

Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks

In this paper we explore acceleration techniques for large scale nonconv...
research
08/22/2018

Convergence of Cubic Regularization for Nonconvex Optimization under KL Property

Cubic-regularized Newton's method (CR) is a popular algorithm that guara...
research
10/12/2022

A Momentum Accelerated Adaptive Cubic Regularization Method for Nonconvex Optimization

The cubic regularization method (CR) and its adaptive version (ARC) are ...
research
05/25/2020

Triangularized Orthogonalization-free Method for Solving Extreme Eigenvalue Problems

A novel orthogonalization-free method together with two specific algorit...

Please sign up or login with your details

Forgot password? Click here to reset