Deep learning techniques for inverse problems in imaging
Recent work in machine learning shows that deep neural networks can be used to solve a
wide variety of inverse problems arising in computational imaging. We explore the central …
wide variety of inverse problems arising in computational imaging. We explore the central …
Deterministic equivalent and error universality of deep random features learning
This manuscript considers the problem of learning a random Gaussian network function
using a fully connected network with frozen intermediate layers and trainable readout layer …
using a fully connected network with frozen intermediate layers and trainable readout layer …
Online stochastic gradient descent on non-convex losses from high-dimensional inference
Stochastic gradient descent (SGD) is a popular algorithm for optimization problems arising
in high-dimensional inference tasks. Here one produces an estimator of an unknown …
in high-dimensional inference tasks. Here one produces an estimator of an unknown …
Instance-optimal compressed sensing via posterior sampling
We characterize the measurement complexity of compressed sensing of signals drawn from
a known prior distribution, even when the support of the prior is the entire space (rather than …
a known prior distribution, even when the support of the prior is the entire space (rather than …
A non-asymptotic framework for approximate message passing in spiked models
Approximate message passing (AMP) emerges as an effective iterative paradigm for solving
high-dimensional statistical problems. However, prior AMP theory--which focused mostly on …
high-dimensional statistical problems. However, prior AMP theory--which focused mostly on …
Theoretical perspectives on deep learning methods in inverse problems
In recent years, there have been significant advances in the use of deep learning methods in
inverse problems such as denoising, compressive sensing, inpainting, and super-resolution …
inverse problems such as denoising, compressive sensing, inpainting, and super-resolution …
Phase retrieval in high dimensions: Statistical and computational phase transitions
We consider the phase retrieval problem of reconstructing a $ n $-dimensional real or
complex signal $\mathbf {X}^\star $ from $ m $(possibly noisy) observations $ Y_\mu=|\sum …
complex signal $\mathbf {X}^\star $ from $ m $(possibly noisy) observations $ Y_\mu=|\sum …
Robust compressed sensing using generative models
We consider estimating a high dimensional signal in $\R^ n $ using a sublinear number of
linear measurements. In analogy to classical compressed sensing, here we assume a …
linear measurements. In analogy to classical compressed sensing, here we assume a …
Towards sample-optimal compressive phase retrieval with sparse and generative priors
Compressive phase retrieval is a popular variant of the standard compressive sensing
problem in which the measurements only contain magnitude information. In this paper …
problem in which the measurements only contain magnitude information. In this paper …
Phase retrieval from incomplete data via weighted nuclear norm minimization
Recovering an unknown object from the magnitude of its Fourier transform is a phase
retrieval problem. Here, we consider a much difficult case, where those observed intensity …
retrieval problem. Here, we consider a much difficult case, where those observed intensity …