Timezone: »
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.
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
-
2021 : Federating for Learning Group Fair Models »
Afroditi Papadaki · Natalia Martinez · Martin Bertran · Guillermo Sapiro · Miguel Rodrigues -
2021 : Distributionally Robust Group Backwards Compatibility »
Martin Bertran · Natalia Martinez · Guillermo Sapiro -
2021 : Complexity in Facial dynamics using Computer Vision as Behavioral Assessment for Autism Spectrum Disorder »
Pradeep Raj Krishnappa Babu · J. Matias Di Martino · Kimberley Carpenter · Steven Espinosa · geraldine Dawson · Guillermo Sapiro -
2022 : Improving Generalization with Physical Equations »
Antoine Wehenkel · Jens Behrmann · Hsiang Hsu · Guillermo Sapiro · Gilles Louppe · Joern-Henrik Jacobsen -
2022 : Federated Fairness without Access to Demographics »
Afroditi Papadaki · Natalia Martinez · Martin Bertran · Guillermo Sapiro · Miguel Rodrigues -
2022 : A Large-Scale Observational Study of the Causal Effects of a Behavioral Health Nudge »
Achille Nazaret · Guillermo Sapiro -
2022 : A Tale of Two Food Adventurers: The Challenges and Triumphs of Repeated Food Exposures in Avoidant/Restrictive Food Intake Disorder »
Young Kyung Kim · Juan Matias Di Martino · Julia Nicholas · Ilana Pilato · Alannah Rivera-Cancel · Julia Gianneschi · Jalisa Jackson · Ellen Mines · Nancy Zucker · Guillermo Sapiro -
2022 : Modeling Heart Rate Response to Exercise with Wearables Data »
Achille Nazaret · Sana Tonekaboni · Gregory Darnell · Shirley Ren · Guillermo Sapiro · Andrew Miller -
2020 : Lightning Talk 2: Pareto Robustness for Fairness Beyond Demographics »
Natalia Martinez · Martin Bertran · Afroditi Papadaki · Miguel Rodrigues · Guillermo Sapiro -
2018 : Poster Session »
Phillipp Schoppmann · Patrick Yu · Valerie Chen · Travis Dick · Marc Joye · Ningshan Zhang · Frederik Harder · Olli Saarikivi · Théo Ryffel · Yunhui Long · Théo JOURDAN · Di Wang · Antonio Marcedone · Negev Shekel Nosatzki · Yatharth A Dubey · Antti Koskela · Peter Bloem · Aleksandra Korolova · Martin Bertran · Hao Chen · Galen Andrew · Natalia Martinez · Janardhan Kulkarni · Jonathan Passerat-Palmbach · Guillermo Sapiro · Amrita Roy Chowdhury -
2015 : Computational discussion: Challenges in analyzing large neuroimaging datasets »
Guillermo Sapiro -
2015 Poster: Discriminative Robust Transformation Learning »
Jiaji Huang · Qiang Qiu · Guillermo Sapiro · Robert Calderbank -
2013 Poster: Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching »
Marcelo Fiori · Pablo Sprechmann · Joshua T Vogelstein · Pablo Muse · Guillermo Sapiro -
2013 Spotlight: Robust Multimodal Graph Matching: Sparse Coding Meets Graph Matching »
Marcelo Fiori · Pablo Sprechmann · Joshua T Vogelstein · Pablo Muse · Guillermo Sapiro -
2012 Poster: Topology Constraints in Graphical Models »
Marcelo Fiori · Pablo Muse · Guillermo Sapiro -
2012 Poster: Finding Exemplars from Pairwise Dissimilarities via Simultaneous Sparse Recovery »
Ehsan Elhamifar · Guillermo Sapiro · René Vidal -
2009 Poster: Non-Parametric Bayesian Dictionary Learning for Sparse Image Representations »
Mingyuan Zhou · Haojun Chen · John Paisley · Lu Ren · Guillermo Sapiro · Lawrence Carin -
2009 Oral: Non-Parametric Bayesian Dictionary Learning for Sparse Image Representations »
Mingyuan Zhou · Haojun Chen · John Paisley · Lu Ren · Guillermo Sapiro · Larry Carin -
2008 Poster: SDL: Supervised Dictionary Learning »
Julien Mairal · Francis Bach · Jean A Ponce · Guillermo Sapiro · Andrew Zisserman -
2006 Poster: Stratification Learning: Detecting Mixed Density and Dimensionality in High Dimensional Point Clouds »
Gloria Haro · Gregory Randall · Guillermo Sapiro