Research map / Learning theory and algorithms / Matrix and tensor methods
More Efficient Estimation of Multivariate Additive Models Based on Tensor Decomposition and Penalization
Xu Liu, Heng Lian, Jian Huang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add low-rank tensor decomposition (vs full-rank estimator) (ablation) | tensor multivariate additive model, LASSO · Simulation Scenario 1 (n=200, s=40) | MCC: 0.36 -> 0.78 | Improved |
| add low-rank tensor decomposition (vs full-rank estimator) (ablation) | tensor multivariate additive model, LASSO · Simulation Scenario 1 (n=200, s=40) | median sqrt IMSE: 0.124 -> 1.21e-03 | Improved |
| model the coefficients as a third-order tensor (vs RAM_GL group lasso reduced additive model) | tensor multivariate additive model, LASSO · Simulation Scenario 1 (n=200, s=40) | MCC: 0.27 -> 0.78 | Improved |
| use MCP penalty instead of lasso | proposed estimator · Simulation Scenario 1 (n=200, s=40) | median sqrt IMSE: 1.21e-03 -> 7.86e-04 | Improved |
| use SCAD penalty instead of lasso | proposed estimator · Simulation Scenario 1 (n=200, s=40) | median sqrt IMSE: 1.21e-03 -> 8.71e-04 | Improved |
| use MCP penalty instead of lasso | proposed estimator · Simulation Scenario 1 (n=200, s=40) | MCC: 0.78 -> 0.84 | Improved |
| increase sample size from n=200 to n=500 | proposed estimator, LASSO · Simulation Scenario 1 (s=40) | MCC: 0.78 -> 0.89 | Improved |
| use proposed tensor model instead of linear reduced rank regression | proposed estimator, MCP · Breast cancer CGH/expression | prediction error: 5.96 -> 1.90 | Improved |
| use proposed tensor model instead of linear reduced rank regression | proposed estimator, MCP · Breast cancer CGH/expression | average number of selected genes: 46.73 -> 4.68 | Improved |
| use proposed model instead of RAM_AGL | proposed estimator, MCP · Breast cancer CGH/expression | prediction error and genes selected: 1.13 -> 1.90; 88.79 -> 4.68 | Mixed |
| proposed vs oracle with true ranks fixed (ablation) | proposed estimator, LASSO · Simulation Scenario 2 (n=200, s=40) | MCC: 0.71 -> 0.67 | Hurt |
Closest papers by meaning
- High-Dimensional Tensor Regression With Oracle Properties (ICML 2025 · similarity 0.89)
- Sparse Tensor Additive Regression (JMLR 2021 · similarity 0.88)
- Additive Approximations in High Dimensional Nonparametric Regression via the SALSA (ICML 2016 · similarity 0.87)
- High-dimensional quantile tensor regression (JMLR 2020 · similarity 0.87)
- Efficient Nonparametric Tensor Decomposition for Binary and Count Data (AAAI 2024 · similarity 0.85)
- Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts (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.
