Research map / Optimization / Distributed and compressed
Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking
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 |
|---|---|---|---|
| Jointly use local variance-reduced gradient estimation and decentralized gradient tracking | Decentralized finite-sum non-convex optimization · Finite-sum decentralized non-convex optimization | sample complexity: \mathcal{O}(mn\epsilon^{-1}) -> \mathcal{O}( m\sqrt{n}\epsilon^{-1}) | Helped |
| Jointly use local variance-reduced gradient estimation and decentralized gradient tracking | Decentralized online non-convex optimization · Online decentralized non-convex optimization | sample complexity: \mathcal{O}(m\epsilon^{-2}) -> \mathcal{O}( m \epsilon^{-3/2}) | Helped |
| Jointly use local variance-reduced gradient estimation and decentralized gradient tracking | Decentralized online non-convex optimization · Online decentralized non-convex optimization | communication complexity: \mathcal{O}(\epsilon^{-2}) -> \mathcal{O}(\epsilon^{-1}) | Helped |
| Use gradient tracking with a constant stepsize | D-GET · Finite-sum decentralized non-convex optimization | communication complexity: \mathcal{O}(\epsilon^{-1}) -> \mathcal{O}(\epsilon^{-1}) | No clear effect |
Closest papers by meaning
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.90)
- Faster Adaptive Decentralized Learning Algorithms (ICML 2024 · similarity 0.89)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.89)
- Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods (ICML 2024 · similarity 0.89)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.89)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (AAAI 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.