Sorry, you need to enable JavaScript to visit this website.

Approximate Support Recovery of Atomic Line Spectral Estimation: A Tale of Resolution and Precision

Primary tabs

Citation Author(s):
Submitted by:
Qiuwei Li
Last updated:
10 December 2016 - 3:38pm
Document Type:
Presentation Slides
Document Year:
Presenters Name:
Qiuwei Li
Paper Code:



This work investigates the parameter estimation performance of super-resolution line spectral estimation using atomic norm minimization. The focus is on analyzing the algorithm's accuracy of inferring the frequencies and complex magnitudes from noisy observations. When the Signal-to-Noise Ratio is reasonably high and the true frequencies are separated by $O(\frac{1}{n})$, the atomic norm estimator is shown to localize the correct number of frequencies, each within a neighborhood of size $O(\sqrt{\frac{\log n}{n^3}} \sigma)$ of one of the true frequencies. Here $n$ is half the number of temporal samples and $\sigma^2$ is the Gaussian noise variance. The analysis is based on a primal-dual witness construction procedure. The obtained error bound matches the Cram\'er-Rao lower bound up to a logarithmic factor. The relationship between resolution (separation of frequencies) and precision or accuracy of the estimator is highlighted.

0 users have voted:

Dataset Files