Imperial College London > Talks@ee.imperial > COMMSP Seminar > Hard Thresholding with Norm Constraints

Hard Thresholding with Norm Constraints

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

If you have a question about this talk, please contact Lauren E Noto.

We introduce a new sparse recovery paradigm, where efficient algorithms from combinatorial and convex optimization interface for interpretable and model-based solutions. A highlight is the introduction of a new algorithmic definition of union-of-subspaces models, which we dub as the Polynomial time Modular Approximation Property (PMAP). PMAP rigorously identifies tractable models within the generic union-of-subspaces models, extending the reach of the model-based sparse recovery to a broader set of applications. Synthetic and real data experiments illustrate that our approach can significantly enhance the performance of both hard thresholding methods and convex solvers in sparse recovery.

This talk is part of the COMMSP Seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Changes to Talks@imperial | Privacy and Publicity