LOSSGRAD: Automatic Learning Rate in Gradient Descent
Bartosz Wójcik, Łukasz Maziarka, Jacek Tabor · Schedae Informaticae · 2018
In this paper, we propose a simple, fast and easy to implement algorithm lossgrad (locally optimal step-size in gradient descent), which automatically modies the step-size in gradient descent during neural networks training.Given a function f , a point x, and the gradient ∇xf of f , we aim to nd the step-size h which is (locally) optimal, i.e. satises:Making use of quadratic approximation, we show that the algorithm satises the above assumption.We experimentally show that our method is insensitive to the choice of initial learning rate while achieving results comparable to other methods.