Research map / Learning theory and algorithms / Matrix and tensor methods
Near Optimal Sketching of Low-Rank Tensor Regression
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 |
|---|---|---|---|
| Sketch low-rank tensor regression with an SJLT matrix | OLS tensor regression · Synthetic, n = 106, σz = 0 and σz = 1 | Time (seconds): > 3 × 104 -> 132.93; > 3 × 104 -> 128.65 | Helped |
| Sketch low-rank tensor regression with an SJLT matrix | OLS tensor regression · Synthetic, n = 106, σz = 1 | Scaled objective: 0.9425 -> 0.9901 | Hurt |
| Sketch low-rank tensor regression with an SJLT matrix | OLS tensor regression · MRI, R = 3, 5, and 10 | Time (seconds): 2824.4 -> 196.31; 8137.2 -> 364.09; 26851 -> 761.73 | Helped |
| Sketch low-rank tensor regression with an SJLT matrix | OLS tensor regression · MRI, R = 3, 5, and 10 | Scaled objective: 16.003 -> 17.047; 11.164 -> 11.992; 6.8679 -> 7.3968 | Hurt |
| Use a moderately larger rank than the true rank | OLS and SOLS · Synthetic data | Statistical performance | No clear effect |
| Use a rank smaller than the true rank | OLS and SOLS · Synthetic data | Statistical performance | Hurt |
Closest papers by meaning
- Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix (ICML 2020 · similarity 0.90)
- Boosted Sparse and Low-Rank Tensor Regression (NeurIPS 2018 · similarity 0.89)
- Fast and accurate randomized algorithms for low-rank tensor decompositions (NeurIPS 2021 · similarity 0.89)
- Tensor-Based Sketching Method for the Low-Rank Approximation of Data Streams. (ICLR 2023 · similarity 0.89)
- High-Dimensional Tensor Regression With Oracle Properties (ICML 2025 · similarity 0.88)
- Fast Tensor Completion via Approximate Richardson Iteration (ICML 2025 · 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.