Research map / Optimization / Nonconvex and smooth optimization
Optimal Algorithms for Decentralized Stochastic 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 |
|---|---|---|---|
| Use the proposed method instead of EGD-GT, EGD-Con, or Sliding | Decentralized deterministic VI on fixed networks · Robust linear regression on LiBSVM datasets; star, ring, and grid | communication rounds | Helped |
| Use the proposed method instead of EGD-GT, EGD-Con, or Sliding | Decentralized deterministic VI on time-varying networks · Robust linear regression on LiBSVM datasets; grid topology | communication rounds | Helped |
| Use EGD-Con instead of the proposed method | Decentralized deterministic VI · Robust linear regression on LiBSVM datasets; time-varying ring topology | communication rounds | Helped |
| Use the proposed algorithm rather than EG-Alc-Alg1, EG-Alc-Alg2, or EG-Car with theoretical parameter choices | Non-distributed stochastic VI · Bilinear problems, including policeman and burglar and two test matrices | epochs to convergence | Helped |
| Tune the competing methods' parameters for best convergence | Non-distributed stochastic VI · Bilinear problems | epochs to convergence | Hurt |
| Use the proposed method instead of earlier decentralized methods | Stochastic decentralized VI · Strongly monotone finite-sum VI, fixed and time-varying networks | communication and local complexity | Helped |
Closest papers by meaning
- Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks (NeurIPS 2024 · similarity 0.91)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (AAAI 2024 · similarity 0.89)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.88)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.88)
- Faster Rates For Federated Variational Inequalities (NeurIPS 2026 · similarity 0.88)
- On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization (NeurIPS 2024 · similarity 0.88)
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.