6 papers
Representation Costs in Data Science: Foundations and the Quasi-Banach Spaces of Deep Neural Networks
Greg Ongie, Rahul Parhi
We develop a general framework for analyzing representation costs induced by parameter-space regularizers in data-fitting methods. For an arbitrary parametric method, we define its…
Memory-efficient optimization of implicit neural representations for CT reconstruction
Mahrokh Najaf, Gregory Ongie
Implicit neural representations (INRs) provide a parameter-efficient and fully differentiable image model for CT reconstruction. However, optimizing INRs for CT reconstruction usin…
When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets
Chen Zeno, Hila Manor, Greg Ongie +3
While diffusion models generate high-quality images via probability flow, the theoretical understanding of this process remains incomplete. A key question is when probability flow…
Sampling Theory for Super-Resolution with Implicit Neural Representations
Mahrokh Najaf, Gregory Ongie
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuou…
Towards a Sampling Theory for Implicit Neural Representations
Mahrokh Najaf, Gregory Ongie
Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuou…
Accelerated Optimization of Implicit Neural Representations for CT Reconstruction
Mahrokh Najaf, Gregory Ongie
Inspired by their success in solving challenging inverse problems in computer vision, implicit neural representations (INRs) have been recently proposed for reconstruction in low-d…