Workshop Schedule 

The workshop takes place on July 9th, 2008

   

8:30-8:40       Introduction (Irina Rish)
 
8:40-9:20       Convex relaxations and sparsity in high-dimensional machine learning (Martin Wainwright)
 
9:20-10:10     Invited Talk: Exploiting sparsity in compressed sensing (Richard Baraniuk)
 
10:10-10:30    Low \ell_1-norm and guarantees on sparsifiability (Shai Shalev-Shwartz and Nathan Srebro)

10:30-10:50    Coffee Break

10:50-11:10    Elastic net regularization in learning theory  (Christine De Mol, Ernesto De Vito and Lorenzo Rosasco), slides (pdf)
                         
11:10-11:30    Consistency of the group Lasso and multiple kernel learning (Francis Bach), slides (pdf)

11:30-12:10    Invited Talk: Hierarchical statistical methods in compressive sensing (Lawrence Carin), slides (pdf)

12:10-12:30    Discussion

12:20-14:00    Lunch Break

14:00-14:40   
Invited Talk:   Sparse Eigenvalue Problems and Applications (Gert Lanckriet)

14:40-15:00   Semi-supervised multi-task feature selection for learning discriminative image representations (Ariadna Quattoni, Michael Collins and Trevor Darrell), slides (pdf)

15:00-15:10    break (prepare for "Beyond \ell_1" session :)

15:10-15:30    A norm concentration argument for non-convex regularization (Ata Kaban and Robert J. Durrant), slides (pdf)

15:30-15:50    In defense of \ell_0 (Dongyu Lin, Emily Pitler, Dean P. Foster and Lyle H. Ungar), slides (pdf)

15:50-16:50   Coffee Break and Poster Session.  

                    Consitency of Trace-Norm Minimization (Francis Bach), poster (pdf)

                    Similarity-Based Theoretical Foundation for Sparse Parzen Window Prediction (Maria-Florina Balcan, Avrim Blum and Nathan Srebro), poster (pdf)

                    Multi-objective optimisation of relevance vector machines: selecting sparse features for     face  verification  (Andrew Clark and Richard Everson), poster (pdf)

                    Orthogonal Principal Feature Selection (Ying Cui and Jennifer G. Dy), poster (pdf)

                    Cost-Sensitive Linear Regression with Costly Features (Robby Goetschalckx, Scott Sanner  and Kurt Driessens), poster (pdf)

                     An Automatic Relevance Determination Procedure Based on Akaike Information Criterion for Linear Regression Problems  (Dmitry Kropotov and Dmitry Vetrov), poster (pdf)

                     Discovering a Semantic Basis of Neural Activity Using Simultaneous Sparse Approximation (Mark Palatucci, Tom Mitchell and Han Liu), poster (ppt)

                     Convex-concave selection of functional components
(Marco Signoretto  and Johan A.K. Suykens), poster (pdf)

                     Learning a L1-regularized Gaussian Bayesian network in the space of equivalence classes (Diego Vidaurre, Concha Bielza and  Pedro Larra˜naga), poster (pdf)

16:50-17:30    Invited Talk: Sparse Optimizations for Speech and Audio Processing (Lawrence Saul) 

17:30-18:00    Discussion: Open Questions and Future Directions