Edgar Dobriban

Edgar Dobriban is an Associate Professor of Statistics and Data Science, with a secondary appointment in Computer and Information Science, at the University of Pennsylvania's Department of Statistics and Data Science. His research focuses on statistics and machine learning, particularly at their intersection with AI, including topics such as uncertainty quantification, robustness, and high-dimensional asymptotic statistics. He is also involved in organizing academic events and initiatives aimed at fostering collaboration between statistics and AI. His work includes publishing papers on various topics in the field and mentoring PhD students interested in statistics and machine learning.

Edgar Dobriban is a statistician and computer scientist whose research focuses on Statistics, Machine Learning, and AI. His work explores the theoretical foundations of statistical learning, including high-dimensional asymptotics, robustness of machine learning models, and methods for data augmentation. Dobriban has contributed to the development of algorithms for distributed regression, sketching in least squares, and adversarially robust classification. His research also addresses challenges in large language models, such as jailbreaking and benchmarking. He has published extensively on topics like implicit regularization, permutation methods for PCA, and provable tradeoffs in robust classification.