Comment on “Joint sparse principal component analysis” by S. Yi et al. (Pattern Recognition, vol. 61, pp. 524-536, 2017)

This paper comments on the published work dealing with “Joint sparse principal component analysis” (Pattern Recognition, vol. 61, pp. 524-536, 2017) proposed by S. Yi et al. Joint sparse principal component analysis (JSPCA) was proposed to jointly select useful features and enhance robustness to outliers. This approach is based on a mathematical model. S. Yi et al. proposed a theorem to show that the approach converges to a local optimal solution. In this paper, their proof is rejected.