Research map / Learning theory and algorithms / Kernels and regression theory
ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions
Luigi Carratino, Stefano Vigogna, Daniele Calandriello, Lorenzo Rosasco
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 |
|---|---|---|---|
| replace greedy feature-space centroids with uniformly random centroids (ParK-Uni) (ablation) | ParK · TAXI | RMSE: 312.0 -> 315.7 | Hurt |
| replace greedy feature-space centroids with uniformly random centroids (ParK-Uni) (ablation) | ParK · TAXI | total time (min): 64 -> 18 | Improved |
| replace greedy centroids with random centroids (ParK-Uni) (ablation) | ParK · HIGGS | 1 - AUC: 0.182 -> 0.192 | Hurt |
| replace greedy centroids with random centroids (ParK-Uni) (ablation) | ParK · HIGGS | total time (sec): 504 -> 70 | Improved |
| replace greedy centroids with random centroids (ParK-Uni) (ablation) | ParK · AIRLINE | MSE: 0.760 -> 0.766 | No clear effect |
| replace greedy centroids with random centroids (ParK-Uni) (ablation) | ParK · AIRLINE | total time (sec): 77 -> 33 | Improved |
| replace greedy centroids with random centroids (ParK-Uni) (ablation) | ParK · AIRLINE-CLS | classification error (%): 31.5 -> 31.6 | No clear effect |
| partition feature space with ParK instead of global FALKON | FALKON · TAXI | total time (min): 120 -> 64 | Improved |
| partition feature space with ParK instead of global FALKON | FALKON · HIGGS | total time (sec): 715 -> 504 | Improved |
| partition feature space with ParK instead of global FALKON | FALKON · AIRLINE | total time (sec): 334 -> 77 | Improved |
| partition feature space with ParK instead of global FALKON | FALKON · AIRLINE-CLS | total time (sec): 391 -> 64 | Improved |
| use 6x Nystrom centers per cell in D&C-Falk (v2 vs v1) (ablation) | D&C-Falk · TAXI | RMSE: 356.2 -> 327.4 | Improved |
Later papers that compared with this method
1 later accepted paper reports Park as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Registration beyond Points: General Affine Subspace Alignment via Geodesic Distance on Grassmann Manifold (ICCV 2025 · better on 5 of 5 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Falkon — FALKON: An Optimal Large Scale Kernel Method (NeurIPS 2017) · better on 4 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression (NeurIPS 2024 · similarity 0.88)
- Supervised Kernel Thinning (NeurIPS 2024 · similarity 0.87)
- Computational Efficiency under Covariate Shift in Kernel Ridge Regression (NeurIPS 2025 · similarity 0.87)
- Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning (NeurIPS 2025 · similarity 0.86)
- High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization (ICML 2024 · similarity 0.86)
- Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random Features (ICML 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.
