Research map / Learning theory and algorithms / Matrix and tensor methods
Leverage Score Sampling for Tensor Product Matrices in Input Sparsity Time
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 the proposed leverage-score sampling method instead of Adaptive Sampling | Kernel ridge regression/classification with equal feature or sketch dimensions · MNIST test, NTK | classification error (%): 5.87 -> 5.44 | Helped |
| Use the proposed leverage-score sampling method instead of Adaptive Sampling | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, NTK | RMSE: 4.72 -> 4.71 | Helped |
| Use the proposed leverage-score sampling method instead of Adaptive Sampling | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, Gaussian | RMSE: 4.76 -> 4.76 | No clear effect |
| Use the proposed leverage-score sampling method instead of PolySketch | Kernel ridge regression/classification with equal feature or sketch dimensions · MNIST test, NTK | classification error (%): 5.92 -> 5.44 | Helped |
| Use the proposed leverage-score sampling method instead of PolySketch | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, NTK | RMSE: 4.87 -> 4.71 | Helped |
| Use the proposed leverage-score sampling method instead of PolySketch | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, Gaussian | RMSE: 5.05 -> 4.76 | Helped |
| Use the proposed leverage-score sampling method instead of Accelerated PolySketch | Kernel ridge regression/classification with equal feature or sketch dimensions · MNIST test, NTK | classification error (%): 6.07 -> 5.44 | Helped |
| Use the proposed leverage-score sampling method instead of Accelerated PolySketch | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, NTK | RMSE: 4.93 -> 4.71 | Helped |
| Use the proposed leverage-score sampling method instead of Accelerated PolySketch | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, Gaussian | RMSE: 5.14 -> 4.76 | Helped |
| Use the proposed leverage-score sampling method instead of Fourier Features | Kernel ridge regression with equal feature or sketch dimensions · Location of CT test, Gaussian | RMSE: 4.92 -> 4.76 | Helped |
Closest papers by meaning
- Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition (NeurIPS 2023 · similarity 0.91)
- Near Input Sparsity Time Kernel Embeddings via Adaptive Sampling (ICML 2020 · similarity 0.89)
- The Complexity of Sparse Tensor PCA (NeurIPS 2021 · similarity 0.89)
- SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling (NeurIPS 2016 · similarity 0.89)
- Efficient Leverage Score Sampling for Tensor Train Decomposition (NeurIPS 2024 · similarity 0.88)
- Fast Sampling-Based Sketches for Tensors (ICML 2024 · similarity 0.87)
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.