The Lingering of Gradients: How to Reuse Gradients over Time
share
Classically, the time complexity of a first-order method is estimated by its number of gradient computations. In this paper, we study a more refined complexity by taking into account the "lingering" of gradients: once a gradient is computed at x_k, the additional time to compute gradients at x_k+1,x_k+2,... may be reduced. We show how this improves the running time of gradient descent and SVRG. For instance, if the "additional time" scales linearly with respect to the traveled distance, then the "convergence rate" of gradient descent can be improved from 1/T to (-T^1/3). On the empirical side, we solve a hypothetical revenue management problem on the Yahoo! Front Page Today Module application with 4.6m users to 10^-6 error (or 10^-12 dual error) using 6 passes of the dataset.
READ FULL TEXT