Learn More
We study a generalized framework for structured sparsity. It extends the well known methods of Lasso and Group Lasso by incorporating additional constraints on the variables as part of a convex optimization problem. This framework provides a straightforward way of favouring prescribed sparsity patterns, such as orderings, contiguous regions and overlapping(More)
We study the problem of learning a sparse linear regression vector under additional conditions on the structure of its sparsity pattern. We present a family of convex penalty functions, which encode this prior knowledge by means of a set of constraints on the absolute values of the regression coefficients. This family subsumes the ℓ 1 norm and is flexible(More)
INTRODUCTION Mesoamerican nephropathy, also known as chronic kidney disease of unknown etiology, is widespread in Pacific coastal Central America. The cause of the epidemic is unknown, but the disease may be linked to multiple factors, including diet as well as environmental and occupational exposures. As many as 50% of men in some communities have(More)
  • 1