The One World Seminar on the Mathematics of Machine Learning

Apr 7, 2021, 12:00 pm12:00 pm
Event Description

What: The One World Seminar on the Mathematics of Machine Learning

When: Wednesday (April 7, 2021) 12 noon ET (4PM GMT / 6PM CET / 9AM PT / 10AM MT / 11AM CT). The title and abstract are below.

Where: The link to the seminar will be sent on Tuesday (and will also be visible on the website just before the talk).

Speaker: Bubacarr Bah (Research Chair of Data Science, African Institute of Mathematical Sciences, South Africa, and Stellenbosch University, South Africa)

Title: Discrete Optimization Methods for Group Model Selection in Compressed Sensing

Abstract: In this talk we study the problem of signal recovery for group models. More precisely for a given set of groups, each containing a small subset of indices, and for given linear sketches of the true signal vector which is known to be group-sparse in the sense that its support is contained in the union of a small number of these groups, we study algorithms which successfully recover the true signal just by the knowledge of its linear  sketches. We derive model projection complexity results and algorithms for more general  group models than the state-of-the-art. We consider two versions of the classical Iterative Hard Thresholding algorithm (IHT). The  classical version iteratively calculates the exact projection of a vector onto the group model, while the approximate version (AM-IHT) uses a head- and a tail-approximation iteratively. We apply both variants to group models and analyze the two cases where the sensing matrix is a Gaussian matrix and a model expander matrix.