Variable selection in high-dimension with random designs and orthogonal matching pursuit
The Journal of Machine Learning Research
| Hi-index | 35.68 |
A well-known analysis of Tropp and Gilbert shows that orthogonal matching pursuit (OMP) can recover a k-sparse n-dimensional real vector from m=4klog(n) noise-free linear measurements obtained through a random Gaussian measurement matrix with a probability that approaches one as n→∞. This work strengthens this result by showing that a lower number of measurements, m=2klog(n-k) , is in fact sufficient for asymptotic recovery. More generally, when the sparsity level satisfies kmin ≤ k ≤ kmax but is unknown, m=2kmaxlog(n-kmin) measurements is sufficient. Furthermore, this number of measurements is also sufficient for detection of the sparsity pattern (support) of the vector with measurement errors provided the signal-to-noise ratio (SNR) scales to infinity. The scaling m=2klog(n-k) exactly matches the number of measurements required by the more complex lasso method for signal recovery with a similar SNR scaling.