Portrait of Sophia Gunluk

Sophia Gunluk

Lab Representative
PhD
Supervisor
Dhanya Sridhar
Research Topics
Causality
Fairness
Website

Biography

I am a second-year Ph.D. student at Mila and Université de Montréal, supervised by Dhanya Sridhar. My main research interest is in applying tools from causal inference to understand classifiers' robustness and long-term fairness in the strategic classification setting where agents react to classifiers. Before coming to Mila, I received my Bachelor of Science in Computer Science from Cornell University, where I also received minors in Philosophy and Operations Research and Information Engineering (ORIE).

Publications

The Role of Causal Features in Strategic Classification for Robustness and Alignment
Sophia Gunluk
Antonio Gois
Nir Rosenfeld
Nidhi Hegde
Simon Lacoste-Julien
Dhanya Sridhar
In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility i… (see more)n a classification task (e.g., loan repayment). Since a key challenge is the distribution shift induced by users, we turn to causal models, which have been shown to bound the worst-case out-of-distribution (OOD) risk, and establish several new results that link causality and strategic classification. First, we show that causal classification leads to optimal classification error after any sufficiently large adaptation, when the noise is bounded in a certain way. Second, when these assumptions do not hold, we show OOD cross-entropy risk of optimal classifiers decomposes into an OOD bias term and a term arising from not using all observable features, allowing us to determine when causal classifiers have an advantage. Finally, we show that causal classifiers can align long-term incentives between institutions and users, contrasting with previous work that highlights social costs of such approaches. We validate our theory empirically on synthetic data, finding that our results predict behavior in practice.
2026-02-02
Artificial Intelligence and Statistics (poster)
openreview.net
openreview.net