Decision trees are widely used for their low computational cost, good predictive performance, and ability to assess the importance of features. Though often in practice feature selection, theoretical guarantees these methods not well understood. We here obtain a tight finite sample bound selection problem linear regression using single-depth decision trees. examine statistical properties "decis...

We study the problem of sparse recovery in context compressed sensing. This is to minimize sensing error linear measurements by vectors with at most s non-zero entries. develop so-called critical point theory for recovery. done introducing nondegenerate M-stationary points which adequately describe global structure this non-convex optimization problem. show that all are generically nondegenerat...

Abstract We consider the problem of reconstructing a signal from under-determined modulo observations (or measurements). This observation model is inspired by relatively new imaging mechanism called imaging, which can be used to extend dynamic range systems; variations this have also been studied under category phase unwrapping. Signal reconstruction in regime with challenging ill-posed problem...