Research map / Learning theory and algorithms / Kernels and regression theory
Fast DPP Sampling for Nystrom with Application to Kernel Methods
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 |
|---|---|---|---|
| Replace uniform/leverage landmark sampling with c-DPP landmark sampling (DPP-Nystrom) | Nystrom kernel approximation · Ailerons kernel approximation | relative Frobenius/spectral norm error | Helped |
| Use c-DPP landmark sampling instead of uniform sampling for kernel ridge regression | Nystrom kernel ridge regression · 8 regression datasets average | improvement over Unif in error (%): more than 20% on average | Helped |
| Run Gibbs chain for c-DPP sampling instead of exact eigendecomposition sampling | DPP-Nystrom landmark selection · Ailerons and California Housing time-error tradeoff | error vs running time | Helped |
| Use AdapFull/exact leverage scores instead of DPP sampling | Nystrom landmark selection · Ailerons time-error tradeoff | error and running time | Hurt |
| Increase kernel bandwidth (smaller alpha regime) effect on Gibbs chain mixing | Gibbs c-DPP sampler · Ailerons, N=1000 and 4000, c=50 | mixing (error convergence) | No clear effect |
Closest papers by meaning
- Sampling from a k-DPP without looking at all items (NeurIPS 2020 · similarity 0.90)
- Recursive Sampling for the Nystrom Method (NeurIPS 2017 · similarity 0.90)
- Scalable Sampling for Nonsymmetric Determinantal Point Processes (ICLR 2022 · similarity 0.90)
- State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives (NeurIPS 2026 · similarity 0.89)
- Sampling-based Nyström Approximation and Kernel Quadrature (ICML 2023 · similarity 0.89)
- Small coresets via negative dependence: DPPs, linear statistics, and concentration (NeurIPS 2024 · 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.