Manifold Regularized Nuclear Norm Matrix Group Sparse Classifier for Robust Image Classification
To efficiently solve the proposed non‐smooth model, a Nesterov‐accelerated Alternating Direction Method of Multipliers (ADMM) is developed and explicit theoretical guarantees are provided, including a Group Sparse Low‐Rank Restricted Isometry Property (GS‐LRIP) recovery error bound and convergence proof.