Lorenzo Rosasco

Queen Mary Vision Laboratory seminar
————————————

Learning from Examples as an Inverse Problem

Speaker: Lorenzo Rosasco
Department of Computer Science, Universita’ di Genova, Italy

Monday Nov 29th, 11:00am (provisional)
Location: ITL Meeting room, middle level

Abstract

Many works have shown that strong connections relate learning from
examples to regularization techniques for ill-posed inverse problems.
Nevertheless by now there was no formal evidence neither that
learning from examples could be seen as an inverse problem nor
that theoretical results in learning theory could be
independently derived using tools from regularization theory.
In this talk we provide a positive answer to both questions.

Indeed, considering the square loss, we translate the learning problem
in the language of regularization
theory and show that consistency results and optimal
regularization parameter choice can be derived by the
discretization of the corresponding inverse problem.