Research map / Learning theory and algorithms / Kernels and regression theory
Distributed Randomized Sketching Kernel Learning
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 sparse randomized sketching with divide-and-conquer KRR instead of the compared approximate KRR methods | DKRR-RS · cadata, shuttle, and w8a | training time | Helped |
| Use sparse randomized sketching with divide-and-conquer KRR rather than Nyström | KRR · shuttle, m=900 | testing error: 0.25 ± 0.012 -> 0.05±0.001 | Helped |
| Increase sketch dimension from m=900 to m=1500 (ablation) | DKRR-RS · cadata | testing error: 0.19±0.023 -> 0.14 ± 0.056 | Helped |
| Increase sketch dimension from m=900 to m=1500 (ablation) | DKRR-RS · shuttle | training time: 0.30 -> 0.50 | Hurt |
| Increase the number of communication rounds (ablation) | DKRR-RS-CM · connect-4 | upper bound on supported partitions | Helped |
| Add the communication strategy to DKRR-RS (ablation) | DKRR-RS · connect-4 | testing error as partition count grows | Helped |
| Increase the number of partitions (ablation) | DKRR-RS and DKRR-RS-CM · connect-4 | testing error | Hurt |
| Increase sketch dimension m (ablation) | DKRR-RS · cadata, shuttle, and w8a | training time | Hurt |
Closest papers by meaning
- Sketching for Distributed Deep Learning: A Sharper Analysis (NeurIPS 2024 · similarity 0.87)
- Distributed Least Squares in Small Space via Sketching and Bias Reduction (NeurIPS 2024 · similarity 0.86)
- Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis (NeurIPS 2025 · similarity 0.86)
- Supervised Kernel Thinning (NeurIPS 2024 · similarity 0.86)
- Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning (ICLR 2024 · similarity 0.85)
- Sketching for Convex and Nonconvex Regularized Least Squares with Sharp Guarantees (ICLR 2025 · similarity 0.85)
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.