Razieh Nabi

Speaker Details
Presentation Date: 5/17/2024
Session: Afternoon Scientific Session - Bias, Fairness, and Inequality in an Algorithmic Age
Title: Advancing Algorithmic Fairness: A Statistical Learning Approach with Fairness Constraints
Abstract: Statistical machine learning algorithms, crucial in sectors like hiring, finance, and healthcare, risk reinforcing societal biases based on gender, race, religion, among others. To combat this, it's vital to design models adhering to fairness norms. This involves embedding fairness constraints such as 'equal opportunity' [Hardt et al., 2016], ensuring uniform true positive rates across groups, and 'path-specific counterfactual fairness' [Nabi and Shpitser, 2018, Nabi et al., 2019], which restricts the effect of the sensitive feature on the outcome along certain user-specified mediating pathways. Without favoring a specific fairness criterion, we propose a general framework for deriving optimal prediction functions under various constraints. It conceptualizes the learning problem as estimating a constrained functional parameter within a comprehensive statistical model, using a Lagrange-type penalty. Key contributions of our work include a flexible framework for solving constrained optimization problems, closed-form solutions for specific fairness constraints, and an algorithm-neutral approach to fair learning.
Dr. Razieh Nabi is an endowed Rollins Assistant Professor in the Department of Biostatistics and Bioinformatics at Emory Rollins School of Public Health, with the secondary appointment in the department of Computer Science at Emory. She earned her PhD from Johns Hopkins University in 2021. Dr. Nabi's methodological research encompasses a range of topics including addressing both measured and unmeasured confounders in causal inference from observational studies, mediation analysis, ensuring algorithmic fairness, and strategies for dealing with missing and censored data. Her work primarily utilizes graphical models and employs both non-parametric and semi-parametric statistical methods. Razieh Nabi's website.