Quadratic Gradient: Combining Gradient Algorithms and Newton's Method as One

Abstract: It might be inadequate for the line search technique for Newton's method to use only one floating point number. A column vector of the same size as the gradient might be better than a mere float number to accelerate each of the gradient elements with different rates. Moreover, a square matrix of the same order as the Hessian matrix might be helpful to correct the Hessian matrix. Chiang applied something between a column vector and a square matrix, namely a diagonal matrix, to accelerate the gradient and further proposed a faster gradient variant called quadratic gradient. In this paper, we present a new way to build a new version of the quadratic gradient. This new quadratic gradient doesn't satisfy the convergence conditions of the fixed Hessian Newton's method. However, experimental results show that it sometimes has a better performance than the original one in convergence rate. Also, Chiang speculates that there might be a relation between the Hessian matrix and the learning rate for the first-order gradient descent method. We prove that the floating number $\frac{1}{\epsilon + \max {| \lambda_i | }}$ can be a good learning rate of the gradient methods, where $\epsilon$ is a number to avoid division by zero and $\lambda_i$ the eigenvalues of the Hessian matrix.