Lorenzo Rosasco
Wednesday 13th January 2016
Time: 4.00pm
Ground Floor Seminar Room
25 Howland Street, London, W1T 4JG
Less is more: optimal learning with subsampling regularization
Friedrich Miescher Institute for Biomedical Research, Basel, Switzerland
In this talk, we discuss recent results on common techniques for scaling
up nonparametric methods such as kernel methods and Gaussian processes.
In particular, we focus on data dependent and independent sub-sampling
methods, namely Nystrom and random features, and study their
generalization properties within a statistical learning theory
framework. On the one hand we show that these methods can achieve
optimal learning errors while being computational efficient. On the
other hand, we show that subsampling can be seen as a form of
regularization, rather than only a way to speed up computations. [Joint
work with Raffaello Camoriano, Alessandro Rudi.]