Research map / Optimization / Distributed and compressed
Decentralised Learning with Random Features and Distributed Gradient Descent
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 approximately √(nm) random features | Distributed Gradient Descent with Random Features · SUSY, grids and cycles with n=9,25 | classification error: approximately \sqrt{nm} | Helped |
| Use a larger number of samples per network | Distributed Gradient Descent with Random Features · SUSY, cycle topology with n=49 | classification error: nm \approx 10^{3} | Helped |
| Use a larger number of samples per network | Distributed Gradient Descent with Random Features · SUSY, cycle topology with n=100 | classification error: 10^{4} | Helped |
| Use sufficiently many samples | Distributed Gradient Descent with Random Features · SUSY, cycle and grid topologies with n=25,49,100 | optimal stopping time: 10^{3} | Helped |
Closest papers by meaning
- Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up (NeurIPS 2019 · similarity 0.93)
- Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach (ICLR 2022 · similarity 0.91)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.90)
- An Improved Analysis of Gradient Tracking for Decentralized Machine Learning (NeurIPS 2021 · similarity 0.89)
- Implicit Regularization of Decentralized Gradient Descent for Sparse Regression (NeurIPS 2024 · 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.