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.

However, such a manner can hardly characterize each of the instances which may have different underlying distributions.

Socialcontext: Culture, geography, history, aswellasusers' attributes, e.g., languageor technologicalfluency.