RPH-PGD: Randomly Projected Hessian for Perturbed Gradient Descent

Abstract

The perturbed gradient descent (PGD) method, which adds random noises in the search directions, has been widely used in solving large-scale optimization problems, owing to its capability to escape from saddle points. However, it is inefficient sometimes for two reasons. First, the random noises may not point to a descent direction, so PGD may still stagnate around saddle points. Second, the size of random noises, which is controlled by the radius of the perturbation ball, may not be properly configured, so the convergence is slow. In this paper, we proposed a method, called RPH-PGD (Randomly Projected Hessian for Perturbed Gradient Descent), to improve the performance of PGD. The randomly projected Hessian (RPH) is created by projecting the Hessian matrix into a relatively small subspace which contains rich information about the eigenvectors of the original Hessian matrix. RPH-PGD utilizes the eigenvalues and eigenvectors of the randomly projected Hessian to identify the negative curvatures and uses the matrix itself to estimate the changes of Hessian matrices, which is necessary information for dynamically adjusting the radius during the computation. In addition, RPH-PGD employs the finite difference method to approximate the product of the Hessian and vectors, instead of constructing the Hessian explicitly. The amortized analysis shows the time complexity of RPH-PGD is only slightly higher than that of PGD. The experimental results show RPH-PGD does not only converge faster than PGD, but also converges in cases that PGD cannot.