Golnoosh Farnadi

From Fragile to Certified: Wasserstein Audits of Group Fairness Under Distribution Shift

Understanding the role of depth in the neural tangent kernel for overparameterized neural networks.

Data as a Lever: A Neighbouring Datasets Perspective on Predictive Multiplicity

What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models

A Provably Robust Algorithm for Differentially Private Clustered Federated Learning

FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Regularized Low-Rank Adaptation

Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training