Machine Learning Seminar Series
Wednesday, November 19, 2014
3:30 pm - 4:30 pm
Gross Hall 330
Risi Kondor, University of Chicago
12noon lunch and lecture ¿Perspectives in Machine Learning¿ 3:30-4:30pm Seminar reception following Matrices that appear in modern data analysis and machine learning problems often exhibit complex hierarchical structure, which goes beyond what can be uncovered by traditional linear algebra tools, such as eigendecomposition. In this talk I describe a new notion of matrix factorization inspired by multiresolution analysis that can capture structure in matrices at multiple different scales. The resulting Multiresolution Matrix Factorizations (MMFs) not only provide a wavelet basis for sparse approximation, but can also be used for matrix compression and as a prior for matrix completion. The work presented in this talk is joint with Nedelina Teneva and Vikas Garg.