Research map / Learning theory and algorithms / Sample complexity
Stable Learning via Sample Reweighting
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 |
|---|---|---|---|
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=1000, rho=0.5 to 0.9 | RMSE: 1.173 -> 1.141; 1.261 -> 1.130; 1.476 -> 1.225 | Helped |
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=1000, rho=0.5 to 0.9 | RMSE standard deviation: 0.047 -> 0.027; 0.101 -> 0.023; 0.213 -> 0.065 | Helped |
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=1000, rho=0.5 to 0.9 | beta_error: 1.528 -> 1.402; 1.896 -> 1.759; 2.964 -> 2.544 | Helped |
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=500, rho=0.9 | beta_error: 3.241 -> 3.421 | Hurt |
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=500, rho=0.9 | RMSE: 1.382 -> 1.385 | No clear effect |
| Apply SRDO sample reweighting before OLS | OLS · Simulation, n=2000 and n=10000, rho=0.9 | beta_error: 3.184 -> 2.810; 3.168 -> 2.762 | Helped |
| Apply SRDO sample reweighting before OLS | OLS · King County house prices, later built-year periods | prediction error | Helped |
| Apply SRDO sample reweighting before logistic regression | Logistic regression · WeChat Ads age groups | AUC | Helped |
Closest papers by meaning
- Optimal Transport Reweighting for Robust Learning under Spurious Correlations and Label Noise (NeurIPS 2026 · similarity 0.84)
- Improving Generalization via Meta-Learning on Hard Samples (CVPR 2024 · similarity 0.84)
- Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing (NeurIPS 2025 · similarity 0.83)
- Optimizing importance weighting in the presence of sub-population shifts (ICLR 2025 · similarity 0.83)
- Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks (NeurIPS 2025 · similarity 0.83)
- Stability Evaluation through Distributional Perturbation Analysis (ICML 2024 · 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.