Sparse Recovery in Linear Spans and Convex Hulls of Infinite Dictionaries

Add to your list(s) Download to your calendar using vCal

• Vladimir Koltchinskii (Georgia Tech)
• Thursday 03 June 2010, 17:00-18:00
• MR12, CMS, Wilberforce Road, Cambridge, CB3 0WB.

If you have a question about this talk, please contact rbg24.

We will discuss problems of recovery of “sparse” approximations of a target function in linear spans or convex hulls of given infinite (not necessarily countable) dictionaries based on noisy observations of this function at random points. The method is based on penalized empirical risk minimization with $L_1$-penalty in the case of linear spans and with entropy penalty in the case of convex hulls. A number of problems in Statistics and in Machine Learning can be studied in this framework and many results of the theory of sparse recovery for finite dictionaries, including sparsity oracle inequalities, can be extended to the case of infinite dictionaries.

http://www.math.gatech.edu/users/vlad

This talk is part of the Statistics series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• MR12, CMS, Wilberforce Road, Cambridge, CB3 0WB
• Machine Learning
• School of Physical Sciences
• Statistical Laboratory info aggregator
• Statistics
• Statistics Group
• bld31
• custom
• rp587

Note that ex-directory lists are not shown.