Imperial College London > Talks@ee.imperial > Featured talks > Sparse and spurious: dictionary learning with noise and outliers
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Sparse and spurious: dictionary learning with noise and outliersAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Pier Luigi Dragotti. Abstract: Sparse modeling has become highly popular in signal processing and machine learning, where many tasks can be expressed as under-determined linear inverse problems. Together with a growing family of low-dimensional signal models, sparse models expressed with signal dictionaries have given rise to a rich set of algorithmic principles combining provably good performance with bounded complexity. In practice, from denoising to inpainting and super-resolution, applications require choosing a “good” dictionary. This key step can be empirically addressed through data-driven principles known as dictionary learning. In this talk I will draw a panorama of dictionary learning for low-dimensional modeling. After reviewing the basic empirical principles of dictionary learning and related matrix factorizations such as PCA , K-means and NMF , we will discuss techniques to learn dictionaries with controlled computational efficiency, as well as a series of recent theoretical results establishing the statistical significance of learned dictionaries even in the presence of noise and outliers. Biography: Rémi Gribonval is a Research Director with Inria in Rennes, France, and the scientific leader of the PANAMA research group on sparse audio processing. A former student at Ecole Normale Supérieure, Paris, he received the Ph. D. degree in applied mathematics from the University of Paris-IX Dauphine in 1999. His research focuses on mathematical signal processing, machine learning, approximation theory and statistics, with an emphasis on low-dimensional modeling, dictionary learning and compressed sensing. In 2011, he was awarded the Blaise Pascal Award of the GAMNI -SMAI by the French Academy of Sciences, and a starting investigator grant from the European Research Council. He founded the series of international workshops SPARS on Signal Processing with Adaptive/Sparse Representations. He is a member of the IEEE Signal Processing Theory and Methods Technical Committee, and an IEEE fellow. This talk is part of the Featured talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsExperimental Solid State Group Seminars (Dept. of Physics) Type the title of a new list here Wind FarmsOther talksFiltering Boundary Value Discrete Time Linear Systems Optimal Co-design of FPGA Implementations for MPC iCore Distinguished Lecture: Evolution of Mobile Air Interface Technology Personalized Chronic Disease Treatment Human Mobility Modeling: Insights and Challenges |