c2368d3d45705a56e51ec5940e187f8d-Paper.pdf
–Neural Information Processing Systems
Specifically,weshowthatthebound is related to the perturbation/noise level and the recovery of the true support of the leading eigenvector as well. We also investigate the estimator of SGEP via imposing a non-convex regularization. Such estimator can achieve the optimal error rate and can recover the sparsity structure as well.
Neural Information Processing Systems
Feb-11-2026, 00:48:01 GMT
- Country:
- Asia > China (0.04)
- Europe > Italy
- North America
- Canada > British Columbia
- United States
- Maryland > Baltimore (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Technology: