Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Holographic Embeddings of Knowledge Graphs

- M. Nickel, L. Rosasco, T. Poggio
- Computer Science, Mathematics
- AAAI
- 16 October 2015

Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic… Expand

Kernels for Vector-Valued Functions: a Review

- M. Álvarez, L. Rosasco, N. Lawrence
- Computer Science, Mathematics
- Found. Trends Mach. Learn.
- 30 June 2011

Kernel methods are among the most popular techniques in machine learning. From a regularization perspective they play a central role in regularization theory as they provide a natural choice for the… Expand

On regularization algorithms in learning theory

- F. Bauer, S. Pereverzyev, L. Rosasco
- Mathematics, Computer Science
- J. Complex.
- 1 February 2007

In this paper we discuss a relation between Learning Theory and Regularization of linear ill-posed inverse problems. It is well known that Tikhonov regularization can be profitably used in the… Expand

Less is More: Nyström Computational Regularization

- A. Rudi, R. Camoriano, L. Rosasco
- Mathematics, Computer Science
- NIPS
- 16 July 2015

We study Nystrom type subsampling approaches to large scale kernel methods, and prove learning bounds in the statistical learning setting, where random sampling and high probability estimates are… Expand

Generalization Properties of Learning with Random Features

- A. Rudi, L. Rosasco
- Mathematics, Computer Science
- NIPS
- 14 February 2016

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved… Expand

On Early Stopping in Gradient Descent Learning

- Y. Yao, L. Rosasco, A. Caponnetto
- Mathematics
- 4 April 2007

AbstractIn this paper we study a family of gradient descent algorithms to approximate the regression function from reproducing kernel Hilbert spaces (RKHSs), the family being characterized by a… Expand

On Learning with Integral Operators

- L. Rosasco, M. Belkin, E. D. Vito
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 1 March 2010

A large number of learning algorithms, for example, spectral clustering, kernel Principal Components Analysis and many manifold methods are based on estimating eigenvalues and eigenfunctions of… Expand

Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review

- T. Poggio, H. Mhaskar, L. Rosasco, B. Miranda, Q. Liao
- Computer Science, Mathematics
- Int. J. Autom. Comput.
- 2 November 2016

The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep… Expand

Manifold Regularization

- F. Odone, L. Rosasco
- 2007

In this lecture we introduce a class of learning algorithms, collectively called manifold regularization algorithms, suited for predicting/classifying data embedded in high-dimensional spaces. We… Expand

- 90
- 11

Nonparametric sparsity and regularization

- L. Rosasco, S. Villa, S. Mosci, M. Santoro, A. Verri
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 13 August 2012

In this work we are interested in the problems of supervised learning and variable selection when the input-output dependence is described by a nonlinear function depending on a few variables. Our… Expand