In my research, I use causal inference and statistics to better understand bias and inequality in AI systems, machine learning, and algorithmic decision making. This work includes developing tools for inequality-aware decision making and more wholistic algorithmic fairness, leveraging counterfactual reasoning to improve model explainability and reduce pre-existing disparities, and reimagining how we use causal modeling formalisms to reason about social categories like race and gender.
My research is generously supported by the Microsoft Research PhD Fellowship.
|Jan 25, 2024
|New preprint release: A New Paradigm for Counterfactual Reasoning in Fairness and Recourse.
|Dec 16, 2023
|Oral presentation at the NeurIPS Workshop on Algorithmic Fairness Through the Lens of Time (NeurIPS AFT2023) on Backtracking Counterfactual Fairness. Thanks to the organizers for a great workshop!
|Aug 15, 2023
|Gave a presentation at the KAIST Data Intelligence Lab in Daejeon, Korea as part of the NYU-KAIST Inclusive AI Workshop. Thanks to everyone at KAIST and especially Professor Stephen Whang and his lab for being such wonderful hosts!
|Jul 29, 2023
|Poster presentations at the ICML 2023 Workshop on Counterfactuals in Minds and Machines on Counterfactuals for the Future as well as Causal Dependence Plots.
|Jun 26, 2023
|New AAAI’23 publication: Counterfactuals for the Future.
Counterfactuals for the FutureProceedings of the AAAI Conference on Artificial Intelligence, Jun 2023
A New Paradigm for Counterfactual Reasoning in Fairness and RecoursearXiv Preprint arXiv:2401.13935, Jun 2024