A New Proximal Iterative Hard Thresholding Method with Extrapolation for \(\ell _0\) Minimization
- 148 Downloads
In this paper, we consider a non-convex problem which is the sum of \(\ell _0\)-norm and a convex smooth function under a box constraint. We propose one proximal iterative hard thresholding type method with an extrapolation step for acceleration and establish its global convergence results. In detail, the sequence generated by the proposed method globally converges to a local minimizer of the objective function. Finally, we conduct numerical experiments to show the proposed method’s effectiveness on comparison with some other efficient methods.
Keywords\(\ell _0\) regularization Proximal operator Hard threshholding Extrapolation Local minimizer Global convergence
This work was partially supported by NSFC (No. 11771288), National key research and development program (No. 2017YFB0202902), the Young Top-notch Talent program of China, and 973 program (No. 2015CB856004).
- 16.Edmunds, B., Peng, Z., Yin, W.: TMAC: a toolbox of modern async-parallel, coordinate, splitting, and stochastic methods. CAM report 16–38, UCLA (2016)Google Scholar
- 19.Li, H., Lin, Z.: Accelerated proximal gradient methods for nonconvex programming. In Advances in Neural Information Processing Systems (NIPS), p. 28. (2015)Google Scholar