Extragradient Sliding for Composite Non-Monotone Variational Inequalities
Abstract: Variational inequalities offer a versatile and straightforward approach to analyzing a broad range of equilibrium problems in both theoretical and practical fields. In this paper, we consider a composite generally non-monotone variational inequality represented as a sum of $L_q$-Lipschitz monotone and $L_p$-Lipschitz generally non-monotone operators. We applied a special sliding version of the classical Extragradient method to this problem and obtain better convergence results. In particular, to achieve $\varepsilon$-accuracy of the solution, the oracle complexity of the non-monotone operator $Q$ for our algorithm is $O\left(L_p2/\varepsilon2\right)$ in contrast to the basic Extragradient algorithm with $O\left((L_p+L_q)2/\varepsilon2\right)$. The results of numerical experiments confirm the theoretical findings and show the superiority of the proposed method.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.