• Publications
  • Influence
Model-Based Compressive Sensing
TLDR
This paper introduces a model-based CS theory that parallels the conventional theory and provides concrete guidelines on how to create model- based recovery algorithms with provable performance guarantees. Expand
  • 1,514
  • 130
  • PDF
Sparse Signal Recovery Using Markov Random Fields
TLDR
We extend the theory of Compressive Sensing (CS) to include signals that are concisely represented in terms of a graphical model. Expand
  • 192
  • 20
  • PDF
A Nearly-Linear Time Framework for Graph-Structured Sparsity
TLDR
We introduce a framework for sparsity structures defined via graphs. Expand
  • 68
  • 15
  • PDF
Solving Linear Inverse Problems Using Gan Priors: An Algorithm with Provable Guarantees
  • V. Shah, C. Hegde
  • Computer Science, Mathematics
  • IEEE International Conference on Acoustics…
  • 23 February 2018
TLDR
We advocate the idea of replacing hand-crafted priors, such as sparsity, with a Generative Adversarial Network (GAN) to solve linear inverse problems such as compressive sensing. Expand
  • 79
  • 11
  • PDF
NuMax: A Convex Approach for Learning Near-Isometric Linear Embeddings
TLDR
We propose a novel framework for the deterministic construction of linear, near-isometric embeddings of a finite set of data points. Expand
  • 67
  • 9
  • PDF
Collaborative Deep Learning in Fixed Topology Networks
TLDR
We propose consensus-based distributed SGD (CDSGD) and its momentum variant, CDMSGD) algorithm for collaborative deep learning over fixed topology networks that enables data parallelization as well as decentralized computation. Expand
  • 68
  • 6
  • PDF
Approximation Algorithms for Model-Based Compressive Sensing
TLDR
We introduce a new framework for model-based CS that leverages additional structure in the signal and provides new recovery schemes that can reduce the number of measurements even further. Expand
  • 54
  • 6
  • PDF
Fast, Sample-Efficient Algorithms for Structured Phase Retrieval
TLDR
We consider the problem of recovering a signal x in R^n, from magnitude-only measurements, y_i = |a_i^T x| for i={1,2...m}. Also known as phase retrieval problem, it is a fundamental challenge in nano-, bio- and astronomical imaging systems, astronomical imaging, and speech processing. Expand
  • 33
  • 4
  • PDF
Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation
TLDR
We study the problem of (provably) learning the weights of a two-layer neural network with quadratic activations. Expand
  • 12
  • 4
  • PDF
Random Projections for Manifold Learning
TLDR
We show that with a small number M of random projections of sample points in ℝN belonging to an unknown K-dimensional Euclidean manifold, the intrinsic dimension (ID) of the sample set can be estimated to high accuracy. Expand
  • 133
  • 3
  • PDF