Research map / Learning theory and algorithms / Kernels and regression theory
Optimal Rates of Distributed Regression with Imperfect Kernels
Hongwei Sun, Qiang Wu
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 bias correction (BCKRR) to distributed kernel ridge regression | distributed KRR (Sobolev and Gaussian kernels) · Synthetic regression f*(x)=min(x,1-x), N=4098, m up to 1024 | mean squared error | Improved |
| use imperfect Gaussian kernel instead of perfect Sobolev kernel | distributed KRR / BCKRR · Synthetic regression, lambda=N^(-2/3) | mean squared error | Mixed |
| tune lambda locally with underregularization instead of fixed theoretical lambda | distributed KRR / BCKRR · Synthetic regression, m up to 1024 | mean squared error | Hurt |
Closest papers by meaning
- Distributed Kernel Ridge Regression with Communications (JMLR 2020 · similarity 0.92)
- Distributed Semi-supervised Learning with Kernel Ridge Regression (JMLR 2017 · similarity 0.91)
- Optimal Convergence Rates for Distributed Nystroem Approximation (JMLR 2023 · similarity 0.91)
- Distributed Nyström Kernel Learning with Communications (ICML 2021 · similarity 0.91)
- Effective Distributed Learning with Random Features: Improved Bounds and Algorithms (ICLR 2021 · similarity 0.90)
- Supervised Kernel Thinning (NeurIPS 2024 · similarity 0.87)
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.
