Search Results

Documents authored by Rosasco, Lorenzo

Document
DOI: 10.4230/DagRep.5.8.54
Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361)

Authors: Matthias Hein, Gabor Lugosi, and Lorenzo Rosasco

Published in: Dagstuhl Reports, Volume 5, Issue 8 (2016)

Abstract
Machine learning has become a core field in computer science. Over the last decade the statistical machine learning approach has been successfully applied in many areas such as bioinformatics, computer vision, robotics and information retrieval. The main reasons for the success of machine learning are its strong theoretical foundations and its multidisciplinary approach integrating aspects of computer science, applied mathematics, and statistics among others. The goal of the seminar was to bring together again experts from computer science, mathematics and statistics to discuss the state of the art in machine learning and identify and formulate the key challenges in learning which have to be addressed in the future. The main topics of this seminar were: - Interplay between Optimization and Learning, - Learning Data Representations.
Cite as

Matthias Hein, Gabor Lugosi, and Lorenzo Rosasco. Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361). In Dagstuhl Reports, Volume 5, Issue 8, pp. 54-73, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)

Copy BibTex To Clipboard

@Article{hein_et_al:DagRep.5.8.54,
  author =	{Hein, Matthias and Lugosi, Gabor and Rosasco, Lorenzo},
  title =	{{Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 15361)}},
  pages =	{54--73},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2016},
  volume =	{5},
  number =	{8},
  editor =	{Hein, Matthias and Lugosi, Gabor and Rosasco, Lorenzo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.5.8.54},
  URN =		{urn:nbn:de:0030-drops-56783},
  doi =		{10.4230/DagRep.5.8.54},
  annote =	{Keywords: learning theory, non-smooth optimization (convex and non-convex), signal processing}
}
Document
DOI: 10.4230/DagRep.1.7.53
Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291)

Authors: Matthias Hein, Gabor Lugosi, Lorenzo Rosasco, and Steve Smale

Published in: Dagstuhl Reports, Volume 1, Issue 7 (2011)

Abstract
The main goal of the seminar ``Mathematical and Computational Foundations of Learning Theory'' was to bring together experts from computer science, mathematics and statistics to discuss the state of the art in machine learning broadly construed and identify and formulate the key challenges in learning which have to be addressed in the future. This Dagstuhl seminar was one of the first meetings to cover the full broad range of facets of modern learning theory. The meeting was very successful and all participants agreed that such a meeting should take place on a regular basis.
Cite as

Matthias Hein, Gabor Lugosi, Lorenzo Rosasco, and Steve Smale. Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291). In Dagstuhl Reports, Volume 1, Issue 7, pp. 53-69, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2011)

Copy BibTex To Clipboard

@Article{hein_et_al:DagRep.1.7.53,
  author =	{Hein, Matthias and Lugosi, Gabor and Rosasco, Lorenzo and Smale, Steve},
  title =	{{Mathematical and Computational Foundations of Learning Theory (Dagstuhl Seminar 11291)}},
  pages =	{53--69},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2011},
  volume =	{1},
  number =	{7},
  editor =	{Hein, Matthias and Lugosi, Gabor and Rosasco, Lorenzo and Smale, Steve},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.1.7.53},
  URN =		{urn:nbn:de:0030-drops-33093},
  doi =		{10.4230/DagRep.1.7.53},
  annote =	{Keywords: learning theory, machine learning, sparsity, high-dimensional geometry, manifold learning, online learning}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact