Total Variation Data Analysis - A Non-linear Spectral Framework for Machine Learning
Staff - Faculty of Informatics
Start date: 27 January 2014
End date: 28 January 2014
The Faculty of Informatics is pleased to announce a seminar given by Xavier Bresson
DATE: Monday, January 27th 2014
PLACE: USI Lugano Campus, room SI-008, Informatics building (Via G. Buffi 13)
TIME: 10.30
ABSTRACT:
With enormous and daily flows of data in finance, security, health, social network and multimedia (sound/text/image/video), there is a strong need to process information as efficiently as possible for smart decisions to be made. Machine Learning develops analytical methods and strong algorithms to deal with this massive large-scale, multi-dimensional and multi-modal data. This field has recently seen tremendous advances with the emergence of new powerful techniques combining the key mathematical tools of sparsity, convex optimization and relaxation methods. In this talk, I will present how these concepts can be applied to find excellent approximate solutions of NP-hard balanced cut problems for unsupervised data clustering, significantly overcoming state-of-the-art spectral clustering methods including Shi-Malik's normalized cut. I will also show how to design fast algorithms for the proposed non-convex and non-differentiable optimization problems based on recent breakthroughs in total variation optimization problems borrowed from the compressed sensing field. This new total variation clustering technique paves the way to a new generation of learning algorithms that can provide simultaneously accurate, fast and robust solutions to other fundamental problems in data science such as Support Vector Machine data classification. These new methodologies have a wide range of applications including data retrieval (search engines), neuroimaging (diseases detection and analysis) and social network analysis (community detection).
BIO:
Xavier Bresson is a Postdoctoral Scholar at the University of Lausanne. His main research focuses on mathematical and algorithmic methodologies to tackle data analysis problems in machine learning and computer vision.
In 2005, he completed a Ph.D. at the Swiss Federal Institute of Technology (EPFL). He joined the Department of Mathematics at University of California, Los Angeles (UCLA) as a Postdoctoral Scholar in 2006-2010. He was Assistant Professor with the Computer Science department at the City University of Hong Kong in 2010-2013.
In Feb. 2013, he organized the international workshop on "Convex Relaxation Methods for Geometric Problems in Scientific Computing" at the Institute for Pure and Applied Mathematics (IPAM) at UCLA. In Feb. 2014, he will be a Research Fellow for the Program "Network Science and Graph Algorithms" at the Institute for Computational and Experimental Research in Mathematics (ICERM) at Brown University. He is also organizing the SIAM Conference on Imaging Science in Hong Kong on 12-14 May 2014.
HOST: Prof. Michael Bronstein
