Research map / Learning theory and algorithms / Kernels and regression theory
Kernel quadrature with DPPs
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 DPP-selected nodes with optimized quadrature weights instead of uniform weights on the same DPP nodes | DPPKQ · Periodic Sobolev, d=1, s=3 | squared worst-case quadrature error convergence rate: O(N^{-2s}) vs O(N^{-2}) | Helped |
| Increase leverage-score quadrature regularization | LVSQ · Periodic Sobolev, d=1 | squared worst-case quadrature error convergence | Hurt |
| Use sequential Bayesian quadrature | Sequential Bayesian Quadrature · Periodic Sobolev, d=1, s=3 | squared worst-case quadrature error | Mixed |
| Use DPP-selected nodes with optimized weights rather than DPP nodes with uniform weights | DPPKQ · Korobov, d=2, s=1 | squared quadrature error convergence: O((log N)^{2s(d-1)} N^{-2s}) vs O(N^{-2}) | Helped |
| Use DPPKQ rather than UGBQ in multidimensional Korobov integration | Kernel quadrature · Korobov, d=2, s=1 | squared quadrature error convergence rate: O(N^{-2s/d}) vs O((log N)^{2s(d-1)} N^{-2s}) | Helped |
| Use DPPKQ instead of sequential Bayesian quadrature | Gaussian kernel quadrature · Gaussian kernel, d=1 | squared quadrature error: O(alpha^{N}) vs O(N^{-1}) | Mixed |
| Use DPPKQ rather than Gauss-Hermite Bayesian quadrature | Gaussian kernel quadrature · Gaussian kernel, d=2,3 | squared quadrature error convergence: O(e^{-delta d N^{1/d}}) | Helped |
Closest papers by meaning
- An analysis of Ermakov-Zolotukhin quadrature using kernels (NeurIPS 2021 · similarity 0.91)
- Convergence guarantees for kernel-based quadrature rules in misspecified settings (NeurIPS 2016 · similarity 0.90)
- Positively Weighted Kernel Quadrature via Subsampling (NeurIPS 2022 · similarity 0.89)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · similarity 0.86)
- Kernelized Normalizing Constant Estimation: Bridging Bayesian Quadrature and Bayesian Optimization (AAAI 2024 · similarity 0.85)
- Kernel conditional tests from learning-theoretic bounds (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.