Dr. Gregory Ongie

Dr. Gregory OngieMarquette University

Cudahy Hall, 367

MilwaukeeWI53201United States of America(414) 288-5223gregory.ongie@marquette.eduPersonal Website

Assistant Professor

Department of Mathematical and Statistical Sciences

Courses Taught

• Differential Equations for Biomedical and Civil Engineers
• Theory of Optimization

Research Interests

• Mathematics of deep learning
• Applied algebraic geometry in data science and machine learning
• Machine learning for medical image reconstruction
• Optimization in computational imaging

Publications

• Deep Equilibrium Architectures for Inverse Problems in Imaging, D. Gilton, G. Ongie, R. Willett. IEEE Transactions on Computational Imaging (2021).
• Tensor Methods for Nonlinear Matrix Completion. G. Ongie, L. Balzano, D. Pimentel, R. Willett, R. Nowak. SIAM Journal on Mathematics of Data Science (2021).
• A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case, G. Ongie, R. Willett, D. Soudry, N. Srebro, Proceedings of ICLR (2020).
• Neumann Networks for Linear Inverse Problems in Imaging, D. Gilton, G. Ongie, R. Willett, IEEE Transactions on Computational Imaging (2019).
• Algebraic Variety Models for High-Rank Matrix Completion, G. Ongie, R. Willett, R. Nowak, L. Balzano, Proceedings of ICML (2017).
• Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples, G. Ongie, M. Jacob, SIAM Journal on Imaging Sciences (2016).