Robust multi-view learning via M-estimator joint sparse representation

Yutao Hu, Yulong Wang, Han Li, Hong Chen

Abstract: Highlights•We propose a Robust Multi-view Joint Sparse Representation (RMJSR) method.•We devise an efficient half-quadratic optimization algorithm for RMJSR.•We provide a theoretical guarantee for the proposed method.•A RMJSR based classifier (RMJSRC) is developed for multi-view pattern classification.