Sparse Recovery with Shuffled Labels: Statistical Limits and Practical Estimators
share
This paper considers the sparse recovery with shuffled labels, i.e., = +, where ∈^n, ∈^n× n, ∈^n× p, ∈^p, ∈^n denote the sensing result, the unknown permutation matrix, the design matrix, the sparse signal, and the additive noise, respectively. Our goal is to reconstruct both the permutation matrix and the sparse signal . We investigate this problem from both the statistical and computational aspects. From the statistical aspect, we first establish the minimax lower bounds on the sample number n and the signal-to-noise ratio () for the correct recovery of permutation matrix and the support set (), to be more specific, n ≳ klog p and log≳log n + klog p/n. Then, we confirm the tightness of these minimax lower bounds by presenting an exhaustive-search based estimator whose performance matches the lower bounds thereof up to some multiplicative constants. From the computational aspect, we impose a parsimonious assumption on the number of permuted rows and propose a computationally-efficient estimator accordingly. Moreover, we show that our proposed estimator can obtain the ground-truth (, ()) under mild conditions. Furthermore, we provide numerical experiments to corroborate our claims.
READ FULL TEXT