Upload

Loading icon Loading...

This video is unavailable.

NIPS 2011 Sparse Representation & Low-rank Approximation Workshop: Dictionary-Dependent Penalties...

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to like GoogleTechTalks's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to dislike GoogleTechTalks's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to add GoogleTechTalks's video to your playlist.

Uploaded on Feb 9, 2012

Sparse Representation and Low-rank Approximation Workshop at NIPS 2011

Invited Talk: Dictionary-Dependent Penalties for Sparse Estimation and Rank Minimization by David Wipf, University of California at San Diego

Abstract: In the majority of recent work on sparse estimation algorithms, performance has been evaluated using ideal or quasi-ideal dictionaries (e.g., random Gaussian or Fourier) characterized by unit L2 norm, incoherent columns or features. But these types of dictionaries represent only a subset of the dictionaries that are actually used in practice (largely restricted to idealized compressive sensing applications). In contrast, herein sparse estimation is considered in the context of structured dictionaries possibly exhibiting high coherence between arbitrary groups of columns and/or rows. Sparse penalized regression models are analyzed with the purpose of finding, to the extent possible, regimes of dictionary invariant performance. In particular, a class of non-convex, Bayesian-inspired estimators with dictionary-dependent sparsity penalties is shown to have a number of desirable invariance properties leading to provable advantages over more conventional penalties such as the L1 norm, especially in areas where existing theoretical recovery guarantees no longer hold. This can translate into improved performance in applications such model selection with correlated features, source localization, and compressive sensing with constrained measurement directions. Moreover, the underlying methodology naturally extends to related rank minimization problems.

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

The interactive transcript could not be loaded.

Loading icon Loading...

Loading icon Loading...

Ratings have been disabled for this video.
Rating is available when the video has been rented.
This feature is not available right now. Please try again later.

Loading icon Loading...

Loading...
Working...
to add this to Watch Later

Add to