Research map / Learning theory and algorithms / Prediction and decision losses
Semi-Analytic Resampling in Lasso
Tomoyuki Obuchi, Yoshiyuki Kabashima
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 AMPR instead of direct numerical resampling for stability selection on wine data | Lasso stability selection · Wine quality (white, N_noise=689) | computation time: 2859 s -> 1077 s | Improved |
| add correlation among covariates (common component ratio r_com up to 0.6) | AMPR · Simulated data, N=1000, alpha=0.5 | normalized MSE of beta: less than 0.2 for r_com <= 0.6 | No clear effect |
| raise covariate correlation to r_com=0.8 | AMPR · Simulated data, N=1000, alpha=0.5, lambda=1 | agreement with numerical resampling | Hurt |
| tighten Glmnet convergence threshold from 1e-7 to 1e-10 | Glmnet reference · Simulated data, lambda=0.01 | agreement with AMPR: 10^-7 -> 10^-10 | Improved |
| add noise variables (N_noise=689) to wine data | Lasso · Wine quality (white) | selected support at lambda_opt | No clear effect |
| add damping factor gamma < 0.1 to AMPR update | AMPR · Simulated correlated covariates (r_com=0.8) | convergence: gamma < 0.1 | Improved |
Closest papers by meaning
- A Practical Scheme and Fast Algorithm to Tune the Lasso With Optimality Guarantees (JMLR 2016 · similarity 0.88)
- L1-Regularized Least Squares for Support Recovery of High Dimensional Single Index Models with Gaussian Designs (JMLR 2016 · similarity 0.87)
- A Comparison of Hamming Errors of Representative Variable Selection Methods (ICLR 2022 · similarity 0.87)
- On Coreset for LASSO Regression Problem with Sensitivity Sampling (ICLR 2026 · similarity 0.86)
- Rank-based Lasso - efficient methods for high-dimensional robust model selection (JMLR 2020 · similarity 0.86)
- New Insights for the Multivariate Square-Root Lasso (JMLR 2022 · 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.
