Skip to content
arXiv stat.ML · Papers

Demixing Sparse Signals from Nonlinear Observations using Generalized Non-convex Regularization

arXiv:2607.10618v1 Announce Type: new Abstract: We consider the recovery of a pair of sparse vectors from a limited number of nonlinear observations of their superposition: $y_i=g(inner{ba_i}{bPhibw^ast+bPsibz^ast})+e_i$, $i=1,dots,m$, with $mll n$, incoherent orthonormal bases $bPhi,bPsi$, a scalar link $g