Research map / Optimization / Distributed and compressed
On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum
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 |
|---|---|---|---|
| add momentum to local SCGD (Local-SCGDM) versus no momentum | federated MAML sinewave regression · Sinewave Regression | train/validation loss | Helped |
| inner state momentum gamma smaller (0.3) versus 0.7 (ablation) | Local-SCGDM · Sinewave Regression | validation loss | Mixed |
| number of local epochs p varied (ablation) | Local-SCGDM · Sinewave Regression | train/validation loss | No clear effect |
| momentum coefficient alpha varied (best at 0.9) (ablation) | Local-SCGDM · Sinewave Regression | train/validation loss | Mixed |
| theoretical sample complexity O(1/eps^4) with batch size O(1) and communication O(1/eps^3) via communication period p=T^{1/4} | Local-SCGDM · nonconvex federated compositional optimization (theory) | sample and communication complexity | Helped |
Closest papers by meaning
- A Doubly Recursive Stochastic Compositional Gradient Descent Method for Federated Multi-Level Compositional Optimization (ICML 2024 · similarity 0.92)
- Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization (NeurIPS 2025 · similarity 0.87)
- Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms (ICML 2024 · similarity 0.87)
- How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization? (NeurIPS 2024 · similarity 0.87)
- Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up (ICML 2025 · similarity 0.87)
- Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averaging (ICML 2025 · 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.