Research map / Optimization / Nonconvex and smooth optimization
A Fast Optimistic Method for Monotone Variational Inequalities
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Adding uniform averaging of iterates for GAN training (fOGDA-VI) | fOGDA-VI GAN training · CIFAR-10 GAN, Table 1 | FID: 18.49 -> 17.38 | Helped |
| Use fOGDA-VI instead of LA-GDA for GAN training | GAN training on CIFAR-10 · CIFAR-10 GAN, Table 1 and Table 2 | FID: 15.69 vs 14.09 (best overall) | Hurt |
| Increasing momentum parameter alpha in fOGDA-VI (on matrix game) (ablation) | fOGDA-VI two-player zero sum game · Matrix game d=n=50, natural residual | natural residual convergence speed | Mixed |
| Using fOGDA-VI instead of other methods (EG, Popov, FRB, RG, EAG, ARG) on bilinear matrix game | fOGDA-VI · Two-player zero sum game, natural residual | natural residual | Helped |
| Updating iterator k only every n-th step (n=1000) in GAN training (ablation) | fOGDA-VI GAN training · CIFAR-10 GAN | FID/IS | Mixed |
Closest papers by meaning
- Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities (NeurIPS 2024 · similarity 0.88)
- Solving hidden monotone variational inequalities with surrogate losses (ICLR 2025 · similarity 0.88)
- Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes (ICML 2024 · similarity 0.87)
- Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates (NeurIPS 2026 · similarity 0.86)
- Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions (ICLR 2024 · similarity 0.86)
- A Primal-Dual Approach to Solving Variational Inequalities with General Constraints (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.