Back to list

Lorenzo Rosasco

Visiting scientist

Research Line



77 Massachusetts Avenue


Lorenzo Rosasco is team leader at the Istituto Italiano di Tecnologia (IIT) and  research scientist at the Massachusetts Institute of Technology (MIT). He holds an assistant professor position at the Computer Science Department of the University of Genova, Italy, from which is on leave of absence. He is currently involved in establishing the Computational and Statistical Learning Laboratory, a joint laboratory based on a collaborative agreement between IIT and MIT. He received his PhD from the University of Genova in 2006.  Between  2006 and 2009 he was a postdoctoral fellow at Center for Biological and Computational Learning at the Massachusetts Institute of Technology. His research focuses on studying theory and algorithms for computational learning. Dr. Rosasco has developed and analyzed methods to learn from small as well as large samples of high dimensional data, using analytical and probabilistic tools, within a multidisciplinary approach drawing concepts and techniques primarily from computer science and but also from physics, engineering and applied mathematics. 


His research focuses on studying theory and algorithms for computational learning. Currently his theoretical interests include  1)  foundations and algorithms for  learning data representation; 2) learning and exploiting structure; 3) dynamic learning and large scale computations. The theory and algorithms developed are currently applied  on large scale visual classification tasks and to develop novel  cognitive systems for humanoid robotics.

Selected Publications

Selected publications: 

  • M. Alvarez, N. Lawrence and L. Rosasco., 'Kernels for Vector-Valued Functions: a Review', Foundations and Trends in Machine Learning, Vol. 4, 3, 195-266, 201
  • Smale, S., L. Rosasco, J. Bouvrie, A. Caponnetto, and T. Poggio, 'Mathematics of the Neural Response', Foundations of Computational Mathematics, Vol. 10, 1, 67-91, June 2009 (online); February 2010.
  • De Vito E., Caponnetto A, Rosasco L.. 'Model Selection for Regularized Least-Squares Algorithm in Learning TheoryFoundations of Computational Mathematics Volume 5, Number 1 pp. 59 - 85,2005.


IIT's website uses the following types of cookies: browsing/session, analytics, functional and third party cookies. Users can choose whether or not to accept the use of cookies and access the website. By clicking on "Further Information", the full information notice on the types of cookies will be displayed and you will be able to choose whether or not to accept them whilst browsing on the website
Further Information
Accept and close