Research map / Learning theory and algorithms / Kernels and regression theory
Distributed Kernel Ridge Regression with Communications
Shao-Bo Lin, Di Wang, Ding-Xuan Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add communications (DKRR(l)) to distributed kernel ridge regression | DKRR · Synthetic 1-d data, 10000 training samples | largest usable number of local machines: m approx 40 -> m approx 200 (l=2) | Improved |
| increase the number of communications (ablation) | DKRR(l) · Synthetic data | upper bound of m for MSE close to GMSE: the upper bound m of AECs increases with the number of communications | Improved |
| add communications at large N | DKRR · Synthetic 1-d data, m=180 | MSE: N approx 6000 for d=1 and m=180 | Improved |
| add communications at large N | DKRR · Synthetic 3-d data, m=40 | MSE: N approx 13500 for d=3 and m=40 | Improved |
Closest papers by meaning
- Distributed Nyström Kernel Learning with Communications (ICML 2021 · similarity 0.96)
- Effective Distributed Learning with Random Features: Improved Bounds and Algorithms (ICLR 2021 · similarity 0.93)
- Optimal Convergence Rates for Distributed Nystroem Approximation (JMLR 2023 · similarity 0.93)
- Distributed Semi-supervised Learning with Kernel Ridge Regression (JMLR 2017 · similarity 0.92)
- Optimal Rates of Distributed Regression with Imperfect Kernels (JMLR 2021 · similarity 0.92)
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (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.
