Research map / Learning theory and algorithms / Kernels and regression theory
Estimating Feature-Label Dependence Using Gini Distance Statistics
Silu Zhang, Xin Dang, Dao Nguyen, Dawn E. Wilkins, Yixin Chen
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 Gini distance covariance instead of distance covariance | dependence test · Simulation Exponential, K=3 | power at alpha=0.05: 0.709 -> 0.730 | Improved |
| use Gini distance covariance instead of distance covariance | dependence test · Simulation Exponential, K=5 | power at alpha=0.05: 0.821 -> 0.839 | Improved |
| use Gini distance covariance instead of distance covariance | dependence test · Simulation Normal, K=3 | power at alpha=0.05: 0.977 -> 0.984 | Improved |
| use Gini distance correlation instead of distance correlation | dependence test · Simulation Exponential, K=3 | AUC: 0.890 -> 0.895 | Improved |
| use Gini/distance statistics instead of Pearson R^2 | feature selection with random forest · MNIST | test accuracy | Improved |
| use gCov instead of Pearson R^2 to select genes | feature selection · Breast Cancer (TCGA) | test accuracy | Improved |
| use gCor instead of dCov for ranking features | feature selection · 15 UCI datasets | times top 1: 11 -> 18 | Improved |
| use gCor instead of Pearson R^2 for ranking features | feature selection · 15 UCI datasets | times top 1: 8 -> 18 | Improved |
| use gCor instead of dCov | feature selection · Gene Expression top k=10 | test accuracy: 0.963 -> 0.972 | Improved |
| use gCor instead of dCov | feature selection · Gene Expression top k=5 | test accuracy: 0.889 -> 0.741 | Hurt |
| use gCov instead of dCov for feature ranking | feature selection · MNIST (balanced classes) | feature ranking | No clear effect |
| vary kernel parameter sigma in permutation test (ablation) | gCov/gCor permutation test · simulated mixture n=500 | reject/accept decision | No clear effect |
Closest papers by meaning
- Instance-dependent Label Distribution Estimation for Learning with Label Noise (IJCV 2024 · similarity 0.84)
- Towards Theoretical Understanding of Learning Large-scale Dependent Data via Random Features (ICML 2024 · similarity 0.82)
- Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression (ICLR 2025 · similarity 0.82)
- T-MDML: Triplet-based Multiple Distance Metric Learning for Multi-Instance Multi-Label Classification with Label Correlation (AAAI 2025 · similarity 0.82)
- Reconsidering Feature Structure Information and Latent Space Alignment in Partial Multi-label Feature Selection (AAAI 2025 · similarity 0.82)
- Stabilizing Sample Similarity in Representation via Mitigating Random Consistency (ICML 2025 · similarity 0.82)
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.
