Research map / Optimization / Distributed and compressed
Decentralized Local Stochastic Extra-Gradient for 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 |
|---|---|---|---|
| communicate on full graph only every 5th epoch (Local) instead of every epoch (Full) (ablation) | decentralized extragradient DCGAN · CIFAR-10 DCGAN | FID/Inception Score vs communications | Helped |
| random clique clusters of size 4 each epoch instead of Local full-graph every 5th epoch (ablation) | decentralized extragradient DCGAN · CIFAR-10 DCGAN | FID/Inception Score vs communications | Helped |
| reduce communication (Local/Cluster vs Full) (ablation) | decentralized extragradient DCGAN · CIFAR-10 DCGAN | FID/Inception Score vs local epochs | No clear effect |
Closest papers by meaning
- Optimal Algorithms for Decentralized Stochastic Variational Inequalities (NeurIPS 2022 · similarity 0.90)
- Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks (AAAI 2026 · similarity 0.90)
- Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates (ICLR 2024 · similarity 0.89)
- Faster Rates For Federated Variational Inequalities (NeurIPS 2026 · similarity 0.87)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.87)
- Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm (ICML 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.