Gintare Karolina Dziugaite is a Fundamental Research Scientist at ServiceNow Element AI and Associate Industry Member at Mila. Her research combines theoretical and empirical approaches to understanding deep learning, with a focus on generalization, optimization, and network compression. She has made important contributions to GANs, scaling and understanding the Lottery Ticket Hypothesis, PAC-Bayesian and information-theoretic approaches to learning theory, and non-vacuous generalization bounds. Before joining ServiceNow, she obtained her PhD in machine learning from the University of Cambridge, under the supervision of Zoubin Ghahramani. She studied Mathematics at the University of Warwick and read Part III in Mathematics at the University of Cambridge, completing a Master of Advanced Study (MASt) in Applied Mathematics.
During Winter 2017, she was a long-term participant in the Foundations of Machine Learning program at the Simons Institute for the Theory of Computing at the University of Berkeley, where she started working on generalization in Deep Learning, one of the main topics of her research. She returned to Simons as a fellow in Summer 2019 for the Foundations of Deep Learning program. In 2020, she was a member of the Institute for Advanced Study in Princeton, N.J., participating in the Special Year on Optimization, Statistics, and Theoretical Machine Learning.