Research map / Optimization / Distributed and compressed
Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up
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 |
|---|---|---|---|
| Exploit concentration of local full-batch gradients when tuning step size and stopping time | Distributed Gradient Descent · Decentralised non-parametric regression | excess risk: O((nm)^{-2r/(2r+γ)}) | Helped |
| Use sufficiently many samples per agent so statistical concentration offsets network effects | Distributed Gradient Descent · Big-data regime | iterations: (nm)^{1/(2r+γ)} | Helped |
| Use a single communication round per local gradient step rather than network-dependent multi-step communication | Distributed Gradient Descent · Big-data regime across network topologies | runtime speed-up: of order n | Helped |
| Increase samples per agent | Distributed Gradient Descent · Decentralised non-parametric regression | network error: O(1/m) and O(1/m^2) | Helped |
Closest papers by meaning
- Decentralised Learning with Random Features and Distributed Gradient Descent (ICML 2020 · similarity 0.93)
- DGD^2: A Linearly Convergent Distributed Algorithm For High-dimensional Statistical Recovery (NeurIPS 2022 · similarity 0.89)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.88)
- Communication-Efficient Topologies for Decentralized Learning with $O(1)$ Consensus Rate (NeurIPS 2022 · similarity 0.88)
- Implicit Regularization of Decentralized Gradient Descent for Sparse Regression (NeurIPS 2024 · similarity 0.87)
- Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization (NeurIPS 2024 · similarity 0.86)
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.