Research map / Optimization / Nonconvex and smooth optimization
Efficient Decentralized Stochastic Gradient Descent Method for Nonconvex Finite-Sum Optimization Problems
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 EDSGD instead of DGET, avoiding periodic full-gradient computation | Decentralized finite-sum optimization · Nonconvex finite-sum optimization | sample complexity: O(Kn + Kn1/2/((1−λ)pϵ2)) -> O(K1/2n1/2/((1 − λ)ϵ2)) | Helped |
| Use EDSGD instead of DGET | Decentralized finite-sum optimization · Nonconvex finite-sum optimization | communication complexity: O(1/((1−λ)pϵ2)) -> O(1/((1 − λ)ϵ2)) | Helped |
| Use EDSGD instead of GT-SARAH | Decentralized finite-sum optimization · Nonconvex finite-sum optimization | communication complexity: O(1/((1−λ)3ϵ2)) -> O(1/((1 − λ)ϵ2)) | Helped |
| Avoid periodic full-gradient computation | EDSGD · Logistic regression on six datasets | objective value versus gradient evaluations | Helped |
| Use EDSGD instead of the compared baselines | Decentralized logistic regression · Six classification datasets | gradient norm versus gradient evaluations | Helped |
Closest papers by meaning
- Decentralized Sum-of-Nonconvex Optimization (AAAI 2024 · similarity 0.92)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.91)
- Faster Adaptive Decentralized Learning Algorithms (ICML 2024 · similarity 0.90)
- An Online Optimization Perspective on First-Order and Zero-Order Decentralized Nonsmooth Nonconvex Stochastic Optimization (ICML 2024 · similarity 0.90)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.88)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (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.