We discuss a simple sparse linear problem that is hard to learn with any algorithm that uses a linear combination of the training instances as its weight vector. The hardness holds...
Segmentation of video foreground objects from background has many important applications, such as human computer interaction, video compression, multimedia content editing and man...
Submodular function minimization is a polynomially-solvable combinatorial problem. Unfortunately the best known general-purpose algorithms have high-order polynomial time complexi...
We study the type checking and type inference problems for intuitionistic linear logic: given a System F typed λ-term, (i) for an alleged linear logic type, determine whether the...
Compressed sensing allows perfect recovery of sparse signals (or signals sparse in some basis) using only a small number of measurements. The results in the literature have focuse...
Dmitry M. Malioutov, Sujay Sanghavi, Alan S. Wills...