Timezone: »

 
Poster
Supervised Sparse Analysis and Synthesis Operators
Pablo Sprechmann · Roee Litman · Tal Ben Yakar · Alexander M Bronstein · Guillermo Sapiro

Thu Dec 05 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor
in Poster Session »

In this paper, we propose a new and computationally efficient framework for learning sparse models. We formulate a unified approach that contains as particular cases models promoting sparse synthesis and analysis type of priors, and mixtures thereof. The supervised training of the proposed model is formulated as a bilevel optimization problem, in which the operators are optimized to achieve the best possible performance on a specific task, e.g., reconstruction or classification. By restricting the operators to be shift invariant, our approach can be thought as a way of learning analysis+synthesis sparsity-promoting convolutional operators. Leveraging recent ideas on fast trainable regressors designed to approximate exact sparse codes, we propose a way of constructing feed-forward neural networks capable of approximating the learned models at a fraction of the computational cost of exact solvers. In the shift-invariant case, this leads to a principled way of constructing task-specific convolutional networks. We illustrate the proposed models on several experiments in music analysis and image processing applications.

[ PDF] 

Author Information

Pablo Sprechmann (Duke University)
Roee Litman (Tel Aviv University)
Tal Ben Yakar (Tel Aviv University)
Alexander M Bronstein (Tel Aviv University)
Guillermo Sapiro (Duke University)

More from the Same Authors