Timezone: »

 
Poster
On Fast Leverage Score Sampling and Optimal Learning
Alessandro Rudi · Daniele Calandriello · Luigi Carratino · Lorenzo Rosasco

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #80
in Thu Poster Session B »

Leverage score sampling provides an appealing way to perform approximate com- putations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further approximations. In this paper, we study the problem of leverage score sampling for positive definite ma- trices defined by a kernel. Our contribution is twofold. First we provide a novel algorithm for leverage score sampling and second, we exploit the proposed method in statistical learning by deriving a novel solver for kernel ridge regression. Our main technical contribution is showing that the proposed algorithms are currently the most efficient and accurate for these problems.

Keywords: Kernel Methods · Learning Theory · Regularization
[ Paper] 

Author Information

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

More from the Same Authors