Stochastic methods based on \(\mathcal{VU}\)-decomposition methods for stochastic convex minimax problems (Q1719328)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Stochastic methods based on \(\mathcal{VU}\)-decomposition methods for stochastic convex minimax problems |
scientific article |
Statements
Stochastic methods based on \(\mathcal{VU}\)-decomposition methods for stochastic convex minimax problems (English)
0 references
8 February 2019
0 references
Summary: This paper applies sample average approximation (SAA) method based on \(\mathcal{VU}\)-space decomposition theory to solve stochastic convex minimax problems. Under some moderate conditions, the SAA solution converges to its true counterpart with probability approaching one and convergence is exponentially fast with the increase of sample size. Based on the \(\mathcal{VU}\)-theory, a superlinear convergent \(\mathcal{VU}\)-algorithm frame is designed to solve the SAA problem.
0 references
0 references
0 references
0 references
0 references
0 references