Timezone: »

 
Poster
Nyström Kernel Mean Embeddings
Antoine Chatalic · Nicolas Schreuder · Lorenzo Rosasco · Alessandro Rudi

Thu Jul 21 03:00 PM -- 05:00 PM (PDT) @ Hall E #511
in Poster Session 3 »

Kernel mean embeddings are a powerful tool to represent probability distributions over arbitrary spaces as single points in a Hilbert space. Yet, the cost of computing and storing such embeddings prohibits their direct use in large-scale settings. We propose an efficient approximation procedure based on the Nyström method, which exploits a small random subset of the dataset. Our main result is an upper bound on the approximation error of this procedure. It yields sufficient conditions on the subsample size to obtain the standard (1/sqrt(n)) rate while reducing computational costs. We discuss applications of this result for the approximation of the maximum mean discrepancy and quadrature rules, and we illustrate our theoretical findings with numerical experiments.

Keywords: PM: Monte Carlo and Sampling Methods · T: Learning Theory · MISC: Kernel methods · MISC: Scalable Algorithms · MISC: Unsupervised and Semi-supervised Learning

Author Information

Antoine Chatalic (MaLGa and DIBRIS, Università di Genova (Italy))
Nicolas Schreuder (MALGA, DIBRIS, Università di Genova)
Lorenzo Rosasco (unige, mit, iit)
Alessandro Rudi (INRIA, École Normale Supérieure)

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

More from the Same Authors