Research map / Optimization / Nonconvex and smooth optimization
An adaptive Mirror-Prox method for variational inequalities with singular operators
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 |
|---|---|---|---|
| Use Bregman function of Example 3.4 instead of Euclidean regularization in mirror-prox (ablation) | Mirror-prox · Resource sharing (R=1000 servers, N=100 commodities) | convergence to solution | Helped |
| Add adaptive step-size policy (AMP) instead of constant step-size to mirror-prox (ablation) | Mirror-prox with Bregman regularizer · Resource sharing (R=1000, N=100) | distance to solution vs iterations | Helped |
| Vary constant step-size gamma (0.001, 0.005, 0.010) in mirror-prox (ablation) | Mirror-prox with Bregman regularizer · Resource sharing (R=1000, N=100) | convergence speed | Mixed |
| Run extra-gradient with constant step-sizes (0.001, 0.005, 0.010) on a non-Lipschitz operator (ablation) | Extra-gradient (Euclidean mirror-prox) · Resource sharing (R=1000, N=100) | convergence | Hurt |
| Initialize AMP with a large step-size | Adaptive mirror-prox · Resource sharing (R=1000, N=100) | convergence speed | Helped |
Closest papers by meaning
- Adaptive Proximal Gradient Methods Are Universal Without Approximation (ICML 2024 · similarity 0.87)
- Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates (NeurIPS 2026 · similarity 0.87)
- Mirror Descent-Ascent for mean-field min-max problems (NeurIPS 2026 · similarity 0.87)
- Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes (ICML 2024 · similarity 0.87)
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems (AAAI 2024 · similarity 0.87)
- A Primal-Dual Approach to Solving Variational Inequalities with General Constraints (ICLR 2024 · similarity 0.87)
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.