AI Chat AI Image Generator AI Video Text to Speech

Fully-Decentralized Alternating Projected Gradient Descent for Low Rank column-wise Compressive Sensing

04/18/2022

∙

by Shana Moothedath, et al.

∙

∙

This work develops a provably accurate fully-decentralized fast and communication-efficient alternating projected gradient descent (Dec-AltProjGD) algorithm for solving the following low-rank (LR) matrix recovery problem: recover an LR matrix from independent columnwise linear projections (LR column-wise Compressive Sensing). To our best knowledge, this work is the first attempt to develop a provably correct decentralized algorithm for any problem involving use of an alternating projected GD algorithm and one in which the constraint set to be projected to is a non-convex set.

Shana Moothedath
10 publications
Namrata Vaswani
23 publications

page 1

page 2

page 3

page 4

research

∙ 06/30/2023

A Simple Proof for Efficient Federated Low Rank Matrix Recovery from column-wise Linear Projections

This note provides a significantly simpler and shorter proof of our samp...

0 Namrata Vaswani, et al. ∙

research

∙ 12/26/2021

Fully Decentralized and Federated Low Rank Compressive Sensing

In this work we develop a fully decentralized, federated, and fast solut...

0 Shana Moothedath, et al. ∙

research

∙ 01/30/2018

Fast Binary Compressive Sensing via ℓ_0 Gradient Descent

We present a fast Compressive Sensing algorithm for the reconstruction o...

0 Tianlin Liu, et al. ∙

research

∙ 12/02/2021

Blind Super-resolution of Point Sources via Projected Gradient Descent

Blind super-resolution can be cast as a low rank matrix recovery problem...

0 Sihan Mao, et al. ∙

research

∙ 02/20/2021

Fast and Sample-Efficient Federated Low Rank Matrix Recovery from Column-wise Linear and Quadratic Projections

This work studies the following problem and its magnitude-only extension...

0 Seyedehsara Nayer, et al. ∙

research

∙ 12/02/2020

An algorithm for non-convex off-the-grid sparse spike estimation with a minimum separation constraint

Theoretical results show that sparse off-the-grid spikes can be estimate...

0 Yann Traonmilin, et al. ∙

research

∙ 10/06/2021

Blind Super-resolution via Projected Gradient Descent

Blind super-resolution can be cast as low rank matrix recovery problem b...

0 Sihan Mao, et al. ∙