| Paper ID | SAM-7.4 |
| Paper Title |
ON OVERFITTING IN DISCRETE SUPER-RESOLUTION RECOVERY |
| Authors |
Wenzhe Lu, Heng Qiao, University of Michigan - Shanghai Jiao Tong University Joint Institute, China |
| Session | SAM-7: Detection and Estimation 1 |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Sensor Array and Multichannel Signal Processing: [SAM-CSSM] Compressed sensing and sparse modeling |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
This paper studies the overfitting in discrete super-resolution problem. In particular, we solve for the estimate that simply overfits the noisy measurements. By doing this, we no longer require the prior knowledge of additive noise to set the parameter of sparse reconstruction algorithm to ensure the feasibility of target signal. The analysis of overfitting is based on a new proof of the quotient property of deterministic Fourier measurement matrix as well as a novel insight of the widely used interpolation-based proof technique in super-resolution literature. Our theoretical result shows that a similar stability guarantee holds for the overfitting algorithm as those for non-overfitting ones. The derived error bound is demonstrated by the numerical experiments. |
