Mi Jung is interested in systematically providing individual privacy while still allowing data to be used for clinical and research purposes.

Privacy-preserving machine learning

Mi Jung Park focuses on improving and developing methods in the area of differential privacy, which uses machine learning algorithms to facilitate data use without sacrificing privacy. She is interested in systematically providing individual privacy while still allowing data to be used for clinical and research purposes. Her research program has three main objectives: to improve the trade-offs between privacy and accuracy; to advance differentially-private synthetic data generation techniques; and to study the interplay between differential privacy and other emerging characteristics such as interpretability, fairness and causality. Her work is particularly relevant to applications in healthcare, where analyzing privacy-sensitive data is a must for patients and clinicians alike. The technological solutions that Mi Jung is working toward will help reduce the sensitivity of algorithms to sparse data points, facilitate the sharing of data between healthcare service organizations and improve systems used for human decision-making support through a focus on fairness, causality and interpretability.

Mi Jung is a Canada CIFAR AI Chair at Amii and an Assistant Professor in the Department of Computer Science at the University of British Columbia. Previously, she held the role of Group Leader both at the Max Planck Institute for Intelligent Systems and in Computer Science at the University of Tübingen. She has also held roles in academic and industry research labs. Mi Jung has been a Senior Program Committee Member for the Artificial Intelligence and Statistics conference, the International Conference on Machine Learning and the International Conference on Learning Representations. Publications by Mi Jung have appeared at a number of leading conferences and journals, including the Annual Conference for the Association for the Advancement of Artificial Intelligence, the Journal of Artificial Intelligence Research and the Neural Information Processing Systems Conference.

Publications by Mi Jung have appeared at a number of leading conferences and journals, including the AAAI Conference, JAIR and NeurIPS.