Poster
Optimal Learning for Multi-pass Stochastic Gradient Methods
Junhong Lin · Lorenzo Rosasco
Area 5+6+7+8 #35
Keywords: [ Learning Theory ] [ Convex Optimization ] [ Stochastic Methods ]
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.
Live content is unavailable. Log in and register to view live content