Publications

Google Scholar Page

arXiv.org Pre-prints

Pre-prints

• Enhancing Signal Detectability in Learning-Based CT Reconstruction with a Model Observer Inspired Loss Function.
  M. Lantz, E. Sidky, I. Reiser, X. Pan, G. Ongie. 2024. (code)
• Depth Separation in Norm-Bounded Infinite-Width Neural Networks.
  S. Parkinson, G. Ongie, R. Willett, O. Shamir, N. Srebro. 2024.
• Linear Neural Network Layers Promote Learning Single- and Multiple-Index Models.
  S. Parkinson, G. Ongie, R. Willett. 2023.

Journal and Selected Conference Papers

• How do Minimum-Norm Shallow Denoisers Look in Function Space?.
  C. Zeno, G. Ongie, Y. Blumenfeld, N. Weinberger, D. Soudry. NeurIPS. 2023.
• The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks.
  M.S. Nacson, R. Mulayoff, G. Ongie, T. Michaeli, D. Soudry. International Conference on Learning Representations (ICLR). 2023. (arxiv)
• Deep Equilibrium Architectures for Inverse Problems in Imaging.
  D. Gilton, G. Ongie, R. Willett. IEEE Transactions on Computational Imaging. 2021. (arxiv) (code)
• Model Adaptation for Inverse Problems in Imaging.
  D. Gilton, G. Ongie, R. Willett. IEEE Transactions on Computational Imaging. 2021. (arxiv)
• A Signal Detection Model for Quantifying Over-regularization in Non-linear Image Reconstruction.
  E.Y. Sidky, J.P. Phillips, W. Zhou, G. Ongie, J. Cruz-Bastida, I. S. Reiser, M. A. Anastasio, X. Pan. Medical Physics. 2021. (arxiv)
• Tensor Methods for Nonlinear Matrix Completion.
  G. Ongie, L. Balzano, D. Pimentel, R. Willett, R. Nowak. SIAM Journal on Mathematics of Data Science. 2021. (arxiv) (code)
• Deep Learning Techniques for Inverse Problems in Imaging.
  G. Ongie, A. Jalal, C. Metzler, R. Baraniuk, A. Dimakis, R. Willett. IEEE Journal on Selected Areas in Information Theory. 2020.
• A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case.
  G. Ongie, R. Willett, D. Soudry, N. Srebro. International Conference on Learning Representations (ICLR). 2020. (arxiv) (video)
• Neumann Networks for Linear Inverse Problems in Imaging.
  D. Gilton, G. Ongie, R. Willett. IEEE Transactions on Computational Imaging. 2019. (code)
• Streaming Principal Component Analysis From Incomplete Data.
  A. Eftekhari, G. Ongie, L. Balzano, M. Wakin. Journal of Machine Learning Research. 2019.
• Algebraic Variety Models for High-Rank Matrix Completion.
  G. Ongie, R. Willett, R. Nowak, L. Balzano. International Conference on Machine Learning (ICML). 2017. (code)
• Convex Recovery of Continuous Domain Piecewise Constant Images from Non-Uniform Fourier samples.
  G. Ongie, S. Biswas, M. Jacob. IEEE Transactions on Signal Processing. 2017.
• A Fast Algorithm for Convolutional Structured Low-rank Matrix Recovery.
  G. Ongie & M. Jacob. IEEE Transactions on Computational Imaging. 2017. (code)
• Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples.
  G. Ongie & M. Jacob. SIAM Journal on Imaging Sciences. 2016. (code)
• Recovery of Discontinuous Signals Using Group Sparse Higher Degree Total Variation.
  G. Ongie & M. Jacob. IEEE Signal Processing Letters. 2015.
• Iterative Shrinkage Algorithm for Patch Smoothness Regularized Medical Image Recovery.
  Y. Moshin, G. Ongie, M. Jacob. IEEE Transactions on Medical Imaging. 2014. (code)
• Generalized Higher Degree Total Variation.
  G. Ongie, Y. Hu, S. Ramani, M. Jacob. IEEE Transactions on Image Processing. 2014. (code)

Conference Proceedings

• Investigation of Different Model Observers for Including Signal-Detectability in the Training of CNNs for CT Image Reconstruction.
  G. Ongie, M. Lantz, E. Sidky, I. Reiser, X. Pan. SPIE Medical Imaging. 2024.
• Learning-based Material Decomposition in Dual Energy CT Using an Unrolled Estimator.
  M. Lantz, G. Ongie. IEEE International Symposium on Biomedical Imaging (ISBI). 2023.
• Evaluation of deep learning-based CT reconstruction with a signal-Laplacian model observer.
  G. Ongie, E. Sidky, I. Reiser, X. Pan. CT Meeting. 2022.
• Optimizing model observer performance in learning-based CT reconstruction.
  G. Ongie, E. Sidky, I. Reiser, X. Pan. SPIE Medical Imaging. 2022. (video)
• Model Adaptation for Inverse Problems in Biomedical Imaging.
  D. Gilton, G. Ongie, R. Willett. IEEE International Symposium on Biomedical Imaging (ISBI). 2021.
• Supervised Learning of Model Observers for Assessment of CT Image Reconstruction Algorithms.
  G. Ongie, E. Sidky, I. Reiser, X. Pan. SPIE Medical Imaging. 2020. (video)
• Learned Patch-based Regularization for Inverse Problems in Imaging.
  D. Gilton, G. Ongie, R. Willett. CAMSAP Workshop. 2019.
• Learning to Regularize with Neumann Networks.
  D. Gilton, G. Ongie, R. Willett. IEEE Data Science Workshop. 2019.
• Online Estimation of Coherent Subspaces with Adaptive Sampling.
  G. Ongie, D. Hong, D. Zhang, L. Balzano. SSP Workshop. 2018.
• A Memory-efficient Algorithm for Large-scale Sparsity Regularized Image Reconstruction.
  G. Ongie, N. Murthy, L. Balzano, J. Fessler. Fifth International Conference on Image Formation in X-Ray Computed Tomography. 2018.
• Enhanced Online Subspace Estimation via Adaptive Sensing.
  G. Ongie, D. Hong, D. Zhang, L. Balzano. Asilomar. 2017.
• Low Algebraic Dimension Matrix Completion.
  D. Pimentel, G. Ongie, L. Balzano, R. Willett, R. Nowak. Allerton. 2017.
• Online Dynamic MRI Reconstruction via Robust Subspace Tracking.
  G. Ongie, S. Dewangan, J. Fessler, L. Balzano.. GlobalSIP. 2017. (code)
• Efficient Computation of Regularized Field Map Estimates in 3D.
  G. Ongie, J. Shi, & J. Fessler. ISBI. 2017.
• Structured Low-rank Recovery of Piecewise Constant Signals with Performance Guarantees.
  G. Ongie, S. Biswas, & M. Jacob. ICIP. 2016.
• Accelerated Dynamic MRI Using Structured Low Rank Matrix Completion.
  A. Balachandrasekaran, G. Ongie, & M. Jacob. ICIP. 2016. (code)
• A Fast Algorithm for Structured Low-Rank Matrix Recovery with Applications to Undersampled MRI Reconstruction.
  G. Ongie & M. Jacob. ISBI. 2016. (code)
• Recovery of Piecewise Smooth Images from Few Fourier Samples.
  G. Ongie & M. Jacob. SampTA. 2015.
• Super-resolution MRI Using Finite Rate of Innovation Curves.
  G. Ongie & M. Jacob. ISBI. 2015. (code) Best student paper award winner
• Higher Degree Total Variation for 3-D Image Recovery.
  G. Ongie, Y. Hu, M. Jacob. ISBI. 2014. (code)
• Accelerated MRI Using Iterative Non-local Shrinkage.
  Y. Moshin, G. Ongie, M. Jacob. EMBC. 2014. (code)