Research map / Optimization / Nonconvex and smooth optimization
Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm
Miaoxi Zhu, Li Shen, Bo Du, Dacheng Tao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 a denser communication topology (fully connected instead of ring/star/disconnected) (ablation) | D-SGDA · AUC maximization and GAN stability experiments | parameter distance between perturbed runs (stability) | Improved |
| increase learning rate (ablation) | D-SGDA · AUC maximization and GAN stability experiments | Euclidean distance between weights | Improved |
| increase number of nodes (ablation) | D-SGDA · AUC maximization and GAN stability experiments | Euclidean distance between weights | Hurt |
| increase per-node sample size (ablation) | D-SGDA · AUC maximization and GAN stability experiments | Euclidean distance between weights | Hurt |
Closest papers by meaning
- Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm (ICML 2024 · similarity 0.95)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 2024 · similarity 0.94)
- Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness (ICML 2025 · similarity 0.94)
- Generalization Analysis of Biased Stochastic Gradient Methods for Minimax Problems (NeurIPS 2026 · similarity 0.91)
- Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent (AAAI 2025 · similarity 0.90)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.90)
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.
