Timezone: »

Learning with SGD and Random Features
Luigi Carratino · Alessandro Rudi · Lorenzo Rosasco

Thu Dec 06 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #127

Sketching and stochastic gradient methods are arguably the most common techniques to derive efficient large scale learning algorithms. In this paper, we investigate their application in the context of nonparametric statistical learning. More precisely, we study the estimator defined by stochastic gradient with mini batches and random features. The latter can be seen as form of nonlinear sketching and used to define approximate kernel methods. The considered estimator is not explicitly penalized/constrained and regularization is implicit. Indeed, our study highlights how different parameters, such as number of features, iterations, step-size and mini-batch size control the learning properties of the solutions. We do this by deriving optimal finite sample bounds, under standard assumptions. The obtained results are corroborated and illustrated by numerical experiments.

Author Information

Luigi Carratino (University of Genoa)
Alessandro Rudi (INRIA, Ecole Normale Superieure)
Lorenzo Rosasco (University of Genova- MIT - IIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors