Search Results for author:
Found 5 papers, 1 papers with code
Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions
In this work, we propose and analyze a novel method that overcomes this disadvantage by training a neural network only on subsampled versions of the high-fidelity solution snapshots.
Signal Recovery with Non-Expansive Generative Network Priors
In this work we answer this question, proving that a signal in the range of a Gaussian generative network can be recovered from few linear measurements provided that the width of the layers is proportional to the input layer size (up to log factors).
Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
For both of these inversion algorithms, we introduce a new regularized GAN training algorithm and demonstrate that the learned generative model results in lower reconstruction errors across a wide range of under sampling ratios when solving compressed sensing, inpainting, and super-resolution problems.
Global Convergence of Sobolev Training for Overparameterized Neural Networks
Sobolev loss is used when training a network to approximate the values and derivatives of a target function at a prescribed set of input points.
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
Many problems in statistics and machine learning require the reconstruction of a rank-one signal matrix from noisy data.
