Support Recovery of Sparse Signals from a Mixture of Linear Measurements

Abstract

Recovery of support of a sparse vector from simple measurements is a widely-studied problem, considered under the frameworks of compressed sensing, 1-bit compressed sensing, and more general single index models. We consider generalizations of this problem: mixtures of linear regressions, and mixtures of linear classifiers, where the goal is to recover supports of multiple sparse vectors using only a small number of possibly noisy linear, and 1-bit measurements respectively. The key challenge is that the measurements from different vectors are randomly mixed. Both of these problems have also received attention recently. In mixtures of linear classifiers, the observations correspond to the side of queried hyperplane a random unknown vector lies in, whereas in mixtures of linear regressions we observe the projection of a random unknown vector on the queried hyperplane. The primary step in recovering the unknown vectors from the mixture is to first identify the support of all the individual component vectors. In this work, we study the number of measurements sufficient for recovering the supports of all the component vectors in a mixture in both these models. We provide algorithms that use a number of measurements polynomial in $k,\log n$ and quasi-polynomial in $\ell$, to recover the support of all the $\ell$ unknown vectors in the mixture with high probability when each individual component is a $k$-sparse $n$-dimensional vector.

arXiv comment27 pages, Accepted in NeurIPS 2021

References in corpus (9)

• Lower bounds on the performance of polynomial-time algorithms for sparse linear regression
• Spectral Experts for Estimating Mixtures of Linear Regressions
• Solving a Mixture of Many Random Linear Equations by Tensor Decomposition and Alternating Minimization
• Learning Mixtures of Linear Classifiers
• Superset Technique for Approximate Recovery in One-Bit Compressed Sensing
• Iterative Least Trimmed Squares for Mixed Linear Regression
• Sample Complexity of Learning Mixtures of Sparse Linear Regressions
• Recovery of Sparse Signals from a Mixture of Linear Samples
• Convergence of Parameter Estimates for Regularized Mixed Linear Regression Models