MACHINE LEARNING USING GRADIENT ESTIMATE DETERMINED USING IMPROVED PERTURBATIONS

A method of training a learning network is described. The method includes generating a first estimate of a gradient for the learning network and generating subsequent estimates of the gradient using a feedback network. The feedback network generates improved perturbations for the subsequent gradient estimates. Gradient estimates include the first estimate of the gradient and the subsequent estimates of the gradient. The method also includes using the gradient estimates to determine weights in the learning network. The improved perturbations may include lower variance perturbations.