Practical Applications of Sparse Modeling

Sparse modeling is a rapidly developing area at the intersection of statisticallearning and signal processing, motivated by the age-old statistical problem of selecting a smallnumber of predictive variables in high-dimensional datasets. This collection describes keyapproaches in sparse modeling, focusing on its applications in fields including neuroscience,computational biology, and computer vision.

Sparse modeling methods can improvethe interpretability of predictive models and aid efficient recovery of high-dimensional unobservedsignals from a limited number of measurements. Yet despite significant advances in the field, anumber of open issues remain when sparse modeling meets real-life applications. The book discusses arange of practical applications and state-of-the-art approaches for tackling the challengespresented by these applications. Topics considered include the choice of method in genomicsapplications; analysis of protein mass-spectrometry data; the stability of sparse models in brainimaging applications; sequential testing approaches; algorithmic aspects of sparse recovery; andlearning sparse latent models.

ContributorsA. Vania Apkarian,Marwan Baliki, Melissa K. Carroll, Guillermo A. Cecchi, Volkan Cevher, Xi Chen, Nathan W. Churchill,Remi Emonet, Rahul Garg, Zoubin Ghahramani, Lars Kai Hansen, Matthias Hein, Katherine Heller, SinaJafarpour, Seyoung Kim, Mladen Kolar, Anastasios Kyrillidis, Aurelie Lozano, Matthew L. Malloy,Pablo Meyer, Shakir Mohamed, Alexandru Niculescu-Mizil, Robert D. Nowak, Jean-Marc Odobez, Peter M.Rasmussen, Irina Rish, Saharon Rosset, Martin Slawski, Stephen C. Strother, Jagannadan Varadarajan,Eric P. Xing

Irina Rish, Guillermo Cecchi, and Aurelie Lozao are Research Staff Members at IBM T. J. Watson Research Center, New York. Alexandru Niculescu-Mizil is a Researcher at the Machine Learning Department at NEC Labs America, Princeton, New Jersey.