Research map / Learning theory and algorithms / Matrix and tensor methods
Rank-based Lasso - efficient methods for high-dimensional robust model selection
Wojciech Rejchel, Małgorzata Bogdan
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 RankLasso instead of LADLasso for speed | RankLasso · Simulation, n=400, p=1600 | time ratio: 3087 | Improved |
| use RankLasso instead of cross-validated Lasso under Cauchy noise | RankLasso · Simulation scenarios 1-4 | FDR and power | Improved |
| add adaptive weights to RankLasso with correlated predictors (ablation) | RankLasso · Simulation correlated design | NMP | Improved |
| add thresholding to RankLasso with correlated predictors (ablation) | RankLasso · Simulation correlated design | NMP | Improved |
| use thresholded instead of adaptive RankLasso at equal model size (ablation) | RankLasso · Simulation correlated design | NMP: adaptive: 7 true positives, 3 false discoveries; thresholded: 9 true positives, 1 false discovery | Improved |
| use RankLasso instead of LADLasso when relationship is nonlinear | RankLasso · Simulation scenario 4 | power and FDR | Improved |
| use SNP genotype design instead of Gaussian design | RankLasso · Simulation scenarios 1 vs 2 | NMP | No clear effect |
| add adaptive weights to RankLasso (ablation) | RankLasso · HapMap CCT8 | Ordering prediction quality: 0.74 -> 0.73 | No clear effect |
| add thresholding to RankLasso (ablation) | RankLasso · HapMap PRAME | Ordering prediction quality: 0.61 -> 0.65 (thresholded vs plain) | Improved |
| use RankLasso instead of cross-validated Lasso with outliers | RankLasso · HapMap PRAME | Ordering prediction quality: 0.08 -> 0.65 | Improved |
| use RankLasso instead of LADLasso | RankLasso · HapMap Hs.444277-S | Ordering prediction quality: 0.07 -> 0.59 | Improved |
| use cross-validated Lasso instead of RankLasso with mild outliers | Lasso (CV) · HapMap CCT8 | Ordering prediction quality: 0.74 -> 0.76 | Improved |
Closest papers by meaning
- A Comparison of Hamming Errors of Representative Variable Selection Methods (ICLR 2022 · similarity 0.87)
- Low-Rank-Sparse Subspace Representation for Robust Regression (CVPR 2017 · similarity 0.87)
- Adaptive Reduced Rank Regression (NeurIPS 2020 · similarity 0.87)
- A Practical Scheme and Fast Algorithm to Tune the Lasso With Optimality Guarantees (JMLR 2016 · similarity 0.87)
- Robust Inference for High-Dimensional Linear Models via Residual Randomization (ICML 2021 · similarity 0.86)
- Robust High-Dimensional Low-Rank Matrix Estimation: Optimal Rate and Data-Adaptive Tuning (JMLR 2023 · similarity 0.86)
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.
