Multiple Support Recovery Using Very Few Measurements Per Sample

05/20/2021
by   Lekshmi Ramesh, et al.
0

In the problem of multiple support recovery, we are given access to linear measurements of multiple sparse samples in ℝ^d. These samples can be partitioned into ℓ groups, with samples having the same support belonging to the same group. For a given budget of m measurements per sample, the goal is to recover the ℓ underlying supports, in the absence of the knowledge of group labels. We study this problem with a focus on the measurement-constrained regime where m is smaller than the support size k of each sample. We design a two-step procedure that estimates the union of the underlying supports first, and then uses a spectral algorithm to estimate the individual supports. Our proposed estimator can recover the supports with m<k measurements per sample, from Õ(k^4ℓ^4/m^4) samples. Our guarantees hold for a general, generative model assumption on the samples and measurement matrices. We also provide results from experiments conducted on synthetic data and on the MNIST dataset.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 16

12/24/2019

Sample-Measurement Tradeoff in Support Recovery under a Subgaussian Prior

Data samples from R^d with a common support of size k are accessed throu...
01/30/2021

Phase Transition for Support Recovery from Gaussian Linear Measurements

We study the problem of recovering the common k-sized support of a set o...
06/22/2011

Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals

Standard compressive sensing results state that to exactly recover an s ...
03/05/2021

Error-Correction for Sparse Support Recovery Algorithms

Consider the compressed sensing setup where the support s^* of an m-spar...
01/19/2021

Optimal sampling and assay for soil organic carbon estimation

The world needs around 150 Pg of negative carbon emissions to mitigate c...
03/16/2020

Randomly Aggregated Least Squares for Support Recovery

We study the problem of exact support recovery: given an (unknown) vecto...
07/30/2013

Sharp Threshold for Multivariate Multi-Response Linear Regression via Block Regularized Lasso

In this paper, we investigate a multivariate multi-response (MVMR) linea...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.