He Yiran A hybrid projection-proximal point algorithm is proposed for variational inequality problems. Though the usual proximal point method and its variants require that the mapping involved be monotone, at least pseudomonotone, we assume only that the so-called Minty variational inequality has a solution, in order to ensure the global convergence. This assumption is less stringent than … Read more
Two stability results of the metric regularity under set-valued perturbation are established. As the perturbation is of addition type, the fi rst result assumes that the graph of the sum mapping is locally closed, the perturbation mapping is locally Lipschitz in the sense of Hausdor metric with the diameter of its image at the reference point … Read more
A new extragradient projection method is devised in this paper, which does not obviously require generalized monotonicity and assumes only that the so-called dual variational inequality has a solution in order to ensure its global convergence. In particular, it applies to quasimonotone variational inequality having a nontrivial solution. ArticleDownload View PDF
This paper shows that $p$-order metric regularity is preserved under perturbation of H\”older continuous mapping of order $1/p$, which answers affirmatively a problem posed recently by Dontchev. CitationTechnical report, Department of Mathematics, Chinese University of Hong Kong, 07/2015
We present a double projection algorithm for solving variational inequalities without monotonicity. If the solution of dual variational inequality does exist, then the sequence produced by our method is globally convergent to a solution. Under the same assumption, the sequence produced by known methods has only a subsequence converging to a solution. Numerical experiments are … Read more