Research map / Learning theory and algorithms / Prediction and decision losses
Post-selection inference with HSIC-Lasso
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 |
|---|---|---|---|
| Use HSIC-Lasso with selection-conditioned inference instead of choosing a fixed number of features by HSIC-ordering | Model-free post-selection inference · Artificial data, M1-M4 | power | Mixed |
| Use HSIC-Lasso PSI rather than linear-model PSI | M4, with a cubic feature effect · Artificial data, M4 | power | Helped |
| Use HSIC-Lasso PSI rather than linear-model PSI | M3, a linear data-generating process · Artificial data, M3 | power | Hurt |
| Use the proposed selection-conditioned pivot | HSIC-target testing · Artificial data, M1 and M2 | type-I error: 0.05 | No clear effect |
| Increase the number of screened features | HSIC-Lasso PSI · High-dimensional feature screening | downstream performance | Helped |
| Use an incomplete U-statistic estimator with a larger size | HSIC-Lasso PSI · Artificial data | power | Helped |
| Use adaptive rather than vanilla Lasso regularization | HSIC-Lasso · Additional experiments | number of selected features | Hurt |
| Replace block estimation with incomplete U-statistic estimation | HSIC-Lasso PSI · Artificial data | computational cost | Hurt |
| Use HSIC-Lasso selection instead of HSIC-ordering | Turkish Student Dataset · Turkish Student Dataset | number of selected features | Helped |
Closest papers by meaning
- kernelPSI: a Post-Selection Inference Framework for Nonlinear Variable Selection (ICML 2019 · similarity 0.86)
- On the Consistency of Feature Selection With Lasso for Non-linear Targets (ICML 2016 · similarity 0.86)
- SAND: One-Shot Feature Selection with Additive Noise Distortion (ICML 2025 · similarity 0.84)
- Most Influential Subset Selection: Challenges, Promises, and Beyond (NeurIPS 2024 · similarity 0.83)
- Knockoffs Inference for Partially Linear Models with Automatic Structure Discovery (AAAI 2025 · similarity 0.83)
- Differentially Private High-dimensional Variable Selection via Integer Programming (NeurIPS 2025 · similarity 0.83)
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.