1. Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstruction
2. Global optimality beyond two layers: Training deep relu networks via convex programs;ergen;International Conference on Machine Learning,2021
3. Robust compressed sensing mri with deep generative priors;jalal;Advances in neural information processing systems,2021
4. Convex geometry of two-layer relu networks: Implicit autoencoding and interpretable models;ergen;International Conference on Artificial Intelligence and Statistics,2020
5. Block-Sparse Signals: Uncertainty Relations and Efficient Recovery