Research map / Learning theory and algorithms / Kernels and regression theory
Streaming kernel regression with provably adaptive mean, variance, and regularization
Audrey Durand, Odalric-Ambrym Maillard, Joelle Pineau
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 |
|---|---|---|---|
| tune regularization lambda to sigma^2/C^2 instead of sigma^2 in the concentration bound (ablation) | kernel confidence bound (Theorem) · Synthetic 1D kernel regression (Gaussian kernel, sigma=0.1) | confidence envelope width | Improved |
| use adaptive lambda = sigma_{+,t-1}^2/C^2 instead of fixed lambda = sigma_+^2/C^2 (ablation) | noise upper-bound estimate · Synthetic 1D kernel regression | variance estimate tightness | Improved |
| use fully adaptive regularization with estimated noise instead of fixed lambda with sigma_+ = 1 (ablation) | kernel confidence interval · Synthetic 1D kernel regression (delta=0.1) | confidence interval width | Improved |
| use adaptive regularization instead of fixed lambda = sigma_+^2/C^2 (ablation) | Kernel UCB and Kernel TS · Kernelized bandit, 100 arms, sigma=0.1 | cumulative regret | Improved |
| replace Kernel TS with Kernel UCB | kernelized bandits · Kernelized bandit, 100 arms | cumulative regret | Improved |
| use the new concentration bound instead of the earlier Lemma bound in Kernel TS oracle | Kernel TS · Kernelized bandit, 100 arms | cumulative regret | Improved |
Closest papers by meaning
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.88)
- Learning Theory of Distributed Regression with Bias Corrected Regularization Kernel Network (JMLR 2017 · similarity 0.87)
- Delayed Feedback in Kernel Bandits (ICML 2023 · similarity 0.86)
- Kernel Bayesian Inference with Posterior Regularization (NeurIPS 2016 · similarity 0.86)
- Kernel-based guarantees for nonlinear parametric models in Bayesian optimization (NeurIPS 2026 · similarity 0.86)
- Statistical Inference for Gradient Boosting Regression (NeurIPS 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.
