A globally and linearly convergent PGM for zero-norm regularized quadratic optimization with sphere constraint

This paper is concerned with the zero-norm regularized quadratic optimization with a sphere constraint, which has an important application in sparse eigenvalue problems. For this class of nonconvex and nonsmooth optimization problems, we establish the KL property of exponent 1/2 for its extended-valued objective function and develop a globally and linearly convergent proximal gradient method (PGM). Numerical experiments are included for sparse principal component analysis (PCA) with synthetic and real data to confirm the obtained theoretic results.

Article

Download

View A globally and linearly convergent PGM for zero-norm regularized quadratic optimization with sphere constraint