Research map / Learning theory and algorithms / Fairness
Fair and Optimal Prediction via Post-Processing
Han Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
A talk abstract on characterizing the fairness-accuracy tradeoff in classification and regression and a post-processing algorithm that derives optimal fair predictors from Bayes score functions.
Problem
Inherent tradeoff between fairness and accuracy in classification and regression problems.
Approach
Derives optimal fair predictors from Bayes score functions via a post-processing algorithm, characterizing the fairness-accuracy tradeoff for both classification and regression.
Closest papers by meaning
- Differentially Private Post-Processing for Fair Regression (ICML 2024 · similarity 0.87)
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.85)
- Meta Optimality for Demographic Parity Constrained Regression via Post-Processing (ICML 2025 · similarity 0.85)
- Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysis (NeurIPS 2025 · similarity 0.85)
- A Sequentially Fair Mechanism for Multiple Sensitive Attributes (AAAI 2024 · similarity 0.85)
- Fairness-aware Bayes Optimal Functional Classification (NeurIPS 2025 · similarity 0.84)
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.
