On the Saturation Effect of Kernel Ridge Regression
Yicheng Li, Haobo Zhang, Qian Lin
2023Year
2Citations
16Top-tier citations
Abstract
The saturation effect refers to the phenomenon that the kernel ridge regression (KRR) fails to achieve the information theoretical lower bound when the smoothness of the underground truth function exceeds certain level. The saturation effect has been widely observed in practices and a saturation lower bound of KRR has been conjectured for decades. In this paper, we provide a proof of this long-standing conjecture.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 86f97f36-af64-4929-8805-0a437a0bb082Cited by top-tier papers16
- On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law DecayYicheng Li, Haobo Zhang, Qian LinNeurIPS 2023 · 23 citations
- On the Optimality of Misspecified Kernel Ridge RegressionHaobo Zhang, Yicheng Li, Weihao Lu, Qian LinICML 2023 · 19 citations
- Optimal Rates for Vector-Valued Spectral Regularization Learning AlgorithmsDimitri Meunier, Zikai Shen, Mattes Mollenhauer, Arthur Gretton et al.NeurIPS 2024 · 14 citations
- Smoothness Adaptive Hypothesis Transfer LearningHaotian Lin, Matthew ReimherrICML 2024 · 11 citations
- Towards Understanding Ensemble Distillation in Federated LearningSejun Park, Kihun Hong, Ganguk HwangICML 2023 · 9 citations
Builds on1
Related papers
- Towards a Unified Analysis of Kernel-based Methods Under Covariate ShiftXingdong Feng, Xin He, Caixing Wang, Chao Wang et al.NeurIPS 2023 · 17 citations
- Implicit Regularization of Random Feature ModelsArthur Jacot, Berfin Simsek, Francesco Spadaro, Clément Hongler et al.ICML 2020 · 83 citations
- Optimal Rates for Regularized Conditional Mean Embedding LearningZhu Li, Dimitri Meunier, Mattes Mollenhauer, Arthur GrettonNeurIPS 2022 · 69 citations
- On the Saturation Effects of Spectral Algorithms in Large DimensionsWeihao Lu, Haobo Zhang, Yicheng Li, Qian LinNeurIPS 2024 · 4 citations
- Kernel conditional tests from learning-theoretic boundsPierre-François Massiani, Christian Fiedler, Lukas Haverbeck, Friedrich Solowjow et al.NeurIPS 2025 · 1 citation
