NIPS Proceedingsβ

Optimal Learning for Multi-pass Stochastic Gradient Methods

Part of: Advances in Neural Information Processing Systems 29 (NIPS 2016)

[PDF] [BibTeX] [Supplemental] [Reviews]


Conference Event Type: Poster


We analyze the learning properties of the stochastic gradient method when multiple passes over the data and mini-batches are allowed. In particular, we consider the square loss and show that for a universal step-size choice, the number of passes acts as a regularization parameter, and optimal finite sample bounds can be achieved by early-stopping. Moreover, we show that larger step-sizes are allowed when considering mini-batches. Our analysis is based on a unifying approach, encompassing both batch and stochastic gradient methods as special cases.