Research map / Learning theory and algorithms / Kernels and regression theory
Pointwise Confidence Estimation in the Non-linear $\ell^2$-regularized Least Squares
Ilja Kuzborskij, Yasin Abbasi Yadkori
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 |
|---|---|---|---|
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 10-dimensional, N train 100 | CI coverage (%): 62.25% -> 99.60% | Improved |
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 10-dimensional, N train 20000 | CI coverage (%): 83.00% -> 89.60% | Improved |
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 100-dimensional, N train 100 | CI coverage (%): 31.20% -> 84.40% | Improved |
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 100-dimensional, N train 20000 | mean Winkler interval score: 10.4342 -> 1.7652 | Improved |
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 10-dimensional, N train 100 | mean Winkler interval score: 9.7120 -> 2.3052 | Improved |
| use proposed weighted-norm CI instead of bootstrap | MLP regression · 10-dimensional, N train 20000 | median CI width: 0.1401 -> 0.2333 | Hurt |
| increase training sample size from 100 to 20000 | proposed CI · 100-dimensional | mean Winkler interval score: 8.2162 -> 1.7652 | Improved |
| increase training sample size from 100 to 20000 | proposed CI · 10-dimensional | CI coverage (%): 99.60% -> 89.60% | Mixed |
| increase training sample size from 100 to 20000 | bootstrap CI · 100-dimensional | CI coverage (%): 31.20% -> 60.80% | Hurt |
Closest papers by meaning
- Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning (NeurIPS 2024 · similarity 0.85)
- Regularized least squares learning with heavy-tailed noise is minimax optimal (NeurIPS 2025 · similarity 0.84)
- Bayes-optimal learning of an extensive-width neural network from quadratically many samples (NeurIPS 2024 · similarity 0.84)
- Kernel conditional tests from learning-theoretic bounds (NeurIPS 2025 · similarity 0.84)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.83)
- Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks (NeurIPS 2024 · similarity 0.83)
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.
