Synthetic Data Augmentation for Fairness under Data Imbalance: Theory and Adaptive Allocation
stat.ML, cs.LG, stat.ME
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- One Step to Efficient Synthetic Data
- Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindness
- Auto-Encoding Variational Bayes
- Inherent Trade-Offs in the Fair Determination of Risk Scores
- Bias-Corrected Data Synthesis for Imbalanced Learning
- Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add
- When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
- Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
- Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation
- Conditional Data Synthesis Augmentation
- Classification Imbalance as Transfer Learning
- A Unified Post-Processing Framework for Group Fairness in Classification
- Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
- Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference