Research map / Learning theory and algorithms / Kernels and regression theory
Streaming Kernel PCA with $\tilde{O}(\sqrt{n})$ Random Features
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 O(√n log n) random features under exponential spectral decay | RF-ERM and RF-Oja · KPCA | excess risk: O(1/\sqrt{n}) | Helped |
| Use RF-Oja instead of RF-ERM | KPCA · KPCA | per-iteration cost: $\tilde{O}(k/\epsilon^3) -> \tilde{O}(k/\epsilon)$ | Helped |
| Use RF-Oja instead of RF-ERM | KPCA · KPCA | memory: $\tilde{O}(1/\epsilon^{3}) -> {\tilde{O}(k/\epsilon)}$ | Helped |
| Use Oja's algorithm on random features rather than batch ERM | KPCA · KPCA | memory: $O(n^2)$ | Helped |
| Use RF-ERM or RF-Oja with 750 random features | KPCA · MNIST | population objective: 750 | No clear effect |
Closest papers by meaning
- Oja's Algorithm for Streaming Sparse PCA (NeurIPS 2024 · similarity 0.90)
- Streaming Principal Component Analysis in Noisy Setting (ICML 2018 · similarity 0.90)
- Low Precision Streaming PCA (NeurIPS 2025 · similarity 0.88)
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.85)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.85)
- Rethinking PCA Through Duality (NeurIPS 2025 · similarity 0.84)
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.