We consider a class of learning problems regularized by a structured sparsity-inducing norm defined as the sum of 2- or ∞-norms over groups of variables. Whereas much effort ha...
We consider discrete stochastic optimization problems where the objective function can only be estimated by a simulation oracle; the oracle is defined only at the discrete points....
Abstract A Boolean function is called normal if it is constant on flats of certain dimensions. This property is relevant for the construction and analysis of cryptosystems. This p...
We prove that for any real-valued matrix X ∈ Rm×n , and positive integers r k, there is a subset of r columns of X such that projecting X onto their span gives a r+1 r−k+1 -a...
Abstract. In this paper, a new algorithm for source recovery in underdetermined Sparse Component Analysis (SCA) or atomic decomposition on over-complete dictionaries is presented i...
Hadi Zayyani, Massoud Babaie-Zadeh, G. Hosein Mohi...