AI RESEARCH

Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients

arXiv CS.LG

ArXi:2209.03282v3 Announce Type: replace-cross 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.