Research map / Learning theory and algorithms / Prediction and decision losses
A Randomized Subspace-based Approach for Dimensionality Reduction and Important Variable Selection
Di Bo, Hoon Hwangbo, Vinit Sharma, Corey Arndt, Stephanie TerMaath
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 |
|---|---|---|---|
| Use the simplified GCV trace (A2) instead of the exact recursive trace (A1) (ablation) | Randomized subspace SVR · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE: 11.99 -> 11.64 | Improved |
| Use A2 instead of A1 criterion (ablation) | Randomized subspace SVR · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE standard deviation: 1.12 -> 0.94 | Improved |
| Model interactions with 3-variable subspaces instead of single variables (k=1) (ablation) | Randomized subspace SVR · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE: 12.28 -> 11.64 | Improved |
| Replace RBF kernel with POLY kernel in SVM | SVM · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE: 17.49 -> 12.01 | Improved |
| Use linear models instead of nonlinear random forest | Damage tolerance regression · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE: 14.70 -> 11.89 | Improved |
| Use subspace SVR (A2) instead of partial least squares regression | Damage tolerance regression · Hybrid structure damage tolerance (200 FE runs, 41 vars, 5-fold CV) | RMSE: 11.89 -> 11.64 | Improved |
Closest papers by meaning
- Heterogeneous Sufficient Dimension Reduction and Subspace Clustering (ICML 2025 · similarity 0.81)
- Learning nonlinear level sets for dimensionality reduction in function approximation (NeurIPS 2019 · similarity 0.81)
- High-Dimensional Optimization in Adaptive Random Subspaces (NeurIPS 2019 · similarity 0.81)
- Bayesian Optimization over Hybrid Spaces (ICML 2021 · similarity 0.80)
- Enhancing Sufficient Dimension Reduction via Hellinger Correlation (ICML 2024 · similarity 0.79)
- Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization (ICLR 2025 · similarity 0.78)
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.
