Research map / Optimization / Distributed and compressed
An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums
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 accelerated stochastic proximal updates with randomized pairwise communication | Decentralized finite-sum optimization · Smooth, strongly convex problems on regular graphs | time to accuracy ε: m + √(mκ_s) + (1 + τ)√(κ_s/γ) | Helped |
| Use ADFS instead of Point-SAGA | Decentralized finite-sum optimization · Higgs and Covtype logistic regression; 2D grid networks | idealized time to convergence | Helped |
| Use ADFS instead of MSDA | Decentralized finite-sum optimization · Higgs logistic regression; 2D grid network | idealized time to convergence | Helped |
| Use ADFS instead of DSBA | Decentralized finite-sum optimization · Higgs and Covtype logistic regression; 2D grid networks | idealized time to convergence | Helped |
| Use ADFS instead of ESDACD | Decentralized finite-sum optimization · Higgs and Covtype logistic regression; 2D grid networks | idealized time to convergence | Helped |
| Scale the network from a single machine to n machines | ADFS · Smooth, strongly convex finite sums | time to process data | Helped |
Closest papers by meaning
- On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization (NeurIPS 2024 · similarity 0.90)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.90)
- Enhancing Parallelism in Decentralized Stochastic Convex Optimization (ICML 2025 · similarity 0.89)
- Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations (NeurIPS 2024 · similarity 0.89)
- Faster Adaptive Decentralized Learning Algorithms (ICML 2024 · similarity 0.89)
- Towards Faster Decentralized Stochastic Optimization with Communication Compression (ICLR 2025 · similarity 0.89)
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.