Timezone: »

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

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.

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