5 papers
A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
Floor van Maarschalkerwaart, Subhadip Mukherjee, Christoph Brune +1
Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution during testing differs from the o…
Blessing of Dimensionality for Approximating Sobolev Classes on Manifolds
Hong Ye Tan, Subhadip Mukherjee, Junqi Tang +1
The manifold hypothesis says that natural high-dimensional data lie on or around a low-dimensional manifold. The recent success of statistical and learning-based methods in very hi…
An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts +1
Various tasks in data science are modeled utilizing the variational regularization approach, where manually selecting regularization parameters presents a challenge. The difficulty…
Unsupervised Training of Convex Regularizers using Maximum Likelihood Estimation
Hong Ye Tan, Ziruo Cai, Marcelo Pereyra +3
Imaging is a standard example of an inverse problem, where the task of reconstructing a ground truth from a noisy measurement is ill-posed. Recent state-of-the-art approaches for i…
Practical Operator Sketching Framework for Accelerating Iterative Data-Driven Solutions in Inverse Problems
Junqi Tang, Guixian Xu, Subhadip Mukherjee +1
We propose a new operator-sketching paradigm for designing efficient iterative data-driven reconstruction (IDR) schemes, e.g. Plug-and-Play algorithms and deep unrolling networks.…