Search Results for author:
Found 8 papers, 3 papers with code
A New Paradigm for Counterfactual Reasoning in Fairness and Recourse
The traditional paradigm for counterfactual reasoning in this literature is the interventional counterfactual, where hypothetical interventions are imagined and simulated.
Causal Dependence Plots
Since people often think causally about input-output dependence, CDPs can be powerful tools in the xAI or interpretable machine learning toolkit and contribute to applications like scientific machine learning and algorithmic fairness.
Counterfactuals for the Future
Counterfactuals are often described as 'retrospective,' focusing on hypothetical alternatives to a realized past.
Disaggregated Interventions to Reduce Inequality
We develop a disaggregated approach to tackling pre-existing disparities that relaxes the typical set of assumptions required for the use of social categories in structural causal models.
Causal intersectionality for fair ranking
In this paper we propose a causal modeling approach to intersectional fairness, and a flexible, task-specific method for computing intersectionally fair rankings.
Causal Interventions for Fairness
Most approaches in algorithmic fairness constrain machine learning methods so the resulting predictions satisfy one of several intuitive notions of fairness.
Causal Reasoning for Algorithmic Fairness
In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making.
Counterfactual Fairness
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing.
