Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax Theory

P Chao, E Dobriban - arxiv preprint arxiv:2308.01853, 2023 - arxiv.org
Distribution shifts are a serious concern in modern statistical learning as they can
systematically change the properties of the data away from the truth. We focus on …

Adversarial Robustness for Estimation and Alignment

P Chao - 2024 - repository.upenn.edu
As machine learning models are deployed in a multitude of settings with increasing levels of
influence and competency, there is growing interest in ensuring these models are robust …