labs
seminars
-
Decision-Making & Reasoning: Behavior, Modeling, and Machine Learning – Jab Talk
In the first part of the talk, I will present my work on decision-making and reasoning, usingexperiments paired with computational models to test competing psychological explanations.I will illustrate this line of research with a project examining how people combine privateevidence with social information when making risky decisions, and how modeling can helpreveal the mechanisms underlying… Continue Reading Decision-Making & Reasoning: Behavior, Modeling, and Machine Learning – Jab Talk
-
Computational and Statistical Limits in Modern Machine Learning – Job Talk
Abstract: Modern machine learning systems operate in regimes that challenge classical learning-theoretic assumptions. Models are highly overparameterized, trained with simple optimization algorithms, and rely critically on how data is collected and curated. Understanding the limits of learning in these settings requires revisiting both the computational and statistical foundations of learning theory. A central question in learning… Continue Reading Computational and Statistical Limits in Modern Machine Learning – Job Talk
-
Modern Challenges in Learning Theory – Job Talk
Abstract: Machine learning relies on its ability to generalize from limited data, yet a principled theoretical understanding of generalization remains incomplete. While binary classification is well understood in the classical PAC framework, even its natural extension to multiclass learning is substantially more challenging. In this talk, I will present recent progress in multiclass learning that… Continue Reading Modern Challenges in Learning Theory – Job Talk
-
A machine learning approach to the morphology of human brain ventricles
Abstract: Brain ventricular morphology contains crucial pathological information for neurological conditions including Alzheimer’s disease, Parkinson’s disease, and multiple sclerosis. However, manual segmentation from MRI scans is time-consuming (3-4 hours) and limits large-scale analysis. This work presents a machine learning pipeline for automated ventricular analysis. We developed an Attention U-Net-based model achieving state-of-the-art segmentation in 20… Continue Reading A machine learning approach to the morphology of human brain ventricles
-
Aligning Machine Learning with Society
Machine Learning (ML) systems are increasingly integrated into society, but challenges arise when human incentives and expectations are overlooked. In this talk, I will present frameworks for aligning ML with society, focusing on strategic classification and personalization in decision making. Strategic classification models scenarios where individuals, aware of the deployed classifier, manipulate their observable attributes… Continue Reading Aligning Machine Learning with Society
-
Aligning Machine Learning with Society
Abstract: Machine Learning (ML) systems are increasingly integrated into society, but challenges arise when human incentives and expectations are overlooked. In this talk, I will present frameworks for aligning ML with society, focusing on strategic classification and personalization in decision-making. Strategic classification models scenarios where individuals, aware of the deployed classifier, manipulate their observable attributes… Continue Reading Aligning Machine Learning with Society
-
Differential Privacy via Randomized Sketches
Abstract: Machine learning models trained on personal data are ubiquitous, making it essential to protect individuals’ privacy. Differential privacy (DP) has emerged as the standard framework for privacy-preserving data analysis, providing a formal guarantee that the inclusion or exclusion of any individual has only a limited effect on the output distribution of a computation. At the… Continue Reading Differential Privacy via Randomized Sketches
-
Robust and Actionable ML via Causality
Abstract: Artificial Intelligence is increasingly deployed in high-stakes fields such as healthcare, where two critical challenges emerge: models must generalize to real-world variations and their predictions must be actionable for decision-makers. The generalization challenge arises when AI is applied to data that differs from its training set, a phenomenon known as distribution shift. The actionability challenge… Continue Reading Robust and Actionable ML via Causality
-
Machine-Learning to Trust
Abstract: Can players sustain long-run trust when their equilibrium beliefs are shaped by machine-learning methods that penalize complexity? I study a game in which an infinite sequence of agents with one-period recall decide whether to place trust in their immediate successor. The cost of trusting is state-dependent. Each player’s best response is based on a… Continue Reading Machine-Learning to Trust