Timezone: »

Optimal Learning for Multi-pass Stochastic Gradient Methods
Junhong Lin · Lorenzo Rosasco

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #35 #None

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.

Author Information

Junhong Lin (Istituto Italiano di Tecnologia)
Lorenzo Rosasco (University of Genova- MIT - IIT)

More from the Same Authors