Summer Course and Workshop on Optimization in Machine Learning

May 31 - June 7, 2011 The University of Texas at Austin Austin, Texas, USA

We will be able to reimburse the travel and lodging expenses of a number of Portuguese students (support from the UT Austin | Portugal Program) and of a number of US citizens and permanent residents (support from the Program in Applied and Computational Analysis, Research and Training Group (RTG-NSF) of the University of Texas at Austin, Department of Mathematics & ICES)

This Summer Course and Workshop will be held under the auspices of the international partnership between the University of Texas at Austin and Portuguese Universities, as part of the UT Austin | Portugal Program in the Area of Mathematics (CoLab) and the Program in Applied and Computational Analysis, Research and Training Group (RTG-NSF), UT Austin, Department of Mathematics and the Institute for Computational Engineering and Sciences (ICES). This event is also part of the programs of the Portuguese Operations Research Society (APDIO) and the Portuguese International Center for Mathematics (CIM).

The Summer Course on Optimization in Machine Learning (May 31 - June 3, 2011) will consist of two 10-hour modules given by Katya Scheinberg (Lehigh University) and Nati Srebro (University of Chicago).

The Workshop on Optimization in Machine Learning (June 6-7, 2011) will consist of 60-minute plenary talks and a number of talks and poster presentations. Plenary speakers already confirmed for the workshop are Kristin P. Bennett (Rensselaer Polytechnic Institute), Inderjit S. Dhillon (University of Texas at Austin), Sanjiv Kumar (Google Research), and Lieven Vandenberghe (University of California, Los Angeles).

Organizers: Omar Ghattas (University of Texas at Austin), Katya Scheinberg (Columbia University), and Luis Nunes Vicente (University of Coimbra).

Contact and deadlines: The deadline for the course registration is March 31, 2011. For course and workshop registration please send email to oml2011@math.utexas.edu

Syllabus for the Summer Course

This Summer Course introduces a range of machine learning models and optimization tools that are used to apply these models in practice. For the students with some Machine Learning background the course will introduce what lies behind the optimization tools often used as a black box as well as an understanding of the trade-offs of numerical accuracy and theoretical and empirical complexity. For the students with some Optimization background this course will introduce a variety of applications arising in Machine Learning and Statistics as well as novel optimization methods targeting these applications. The models we will cover include: support vector machines, sparse regression, sparse PCA, collaborative filtering, dimensionality reduction. The optimization methods will include interior point, active set, stochastic gradient, coordinate descent, cutting planes method.