Portrait de Sophia Gunluk

Sophia Gunluk

Représentant du laboratoire
Doctorat
Superviseur⋅e principal⋅e
Dhanya Sridhar
Sujets de recherche
Causalité
Équité
Site web

Biographie

Je suis doctorante en deuxième année à Mila et à l'Université de Montréal, sous la supervision de Dhanya Sridhar. Mes recherches portent principalement sur l'application des outils de l'inférence causale pour comprendre la robustesse des classificateurs et leur équité à long terme dans le cadre de la classification stratégique, où les agents réagissent aux classificateurs. Avant de rejoindre Mila, j'ai obtenu un baccalauréat en informatique à l'Université Cornell, où j'ai également obtenu des mineures en philosophie et en recherche opérationnelle et ingénierie de l'information (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… (voir plus)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