Research map / Learning theory and algorithms / Kernels and regression theory
Nyström Kernel Mean Embeddings
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 a uniform-with-replacement Nyström landmark subset to form the embedding | Kernel mean embedding estimation · Synthetic Gaussian mixture | embedding approximation error: O(1/√n) | Helped |
| Choose the landmark count according to the logarithmic effective-dimension condition | Nyström kernel mean embedding · Exponential spectrum decay | embedding approximation error: m = √n log(√n); O(1/√n) | Helped |
| Use Nyström approximation instead of the empirical estimator | Kernel mean embedding estimation · Fasttext | embedding approximation error | Mixed |
| Use continuous OMP landmarks rather than the Nyström estimator | Kernel mean embedding estimation · Synthetic Gaussian data | embedding approximation error | Mixed |
| Use the Nyström estimator rather than greedy coherence-based or determinant-based heuristics | Kernel mean embedding estimation · Synthetic Gaussian data | embedding approximation error | No clear effect |
| Use a Nyström approximation for the embedding-based MMD estimate | Maximum mean discrepancy estimation · Synthetic and real datasets | MMD estimation error | Helped |
| Use a subsample size determined by polynomial effective-dimension growth | Nyström kernel mean embedding · Polynomial effective dimension | embedding approximation error: m = n1/(2−γ) log(n/δ); O(1/√n) | Helped |
Closest papers by meaning
- Kernel Quantile Embeddings and Associated Probability Metrics (ICML 2025 · similarity 0.89)
- Learning to Embed Distributions via Maximum Kernel Entropy (NeurIPS 2024 · similarity 0.87)
- Random features for Grassmannian kernel approximation with bounded rank-one projections (NeurIPS 2026 · similarity 0.86)
- Gaussian Mixture Models in Hilbert Spaces via Kernel Methods (NeurIPS 2026 · similarity 0.86)
- On the Consistency of Kernel Methods with Dependent Observations (ICML 2024 · similarity 0.86)
- On Statistical Learning Theory for Distributional Inputs (ICML 2024 · similarity 0.86)
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.