Multiple Support Recovery Using Very Few Measurements Per Sample

by   Lekshmi Ramesh, et al.

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.



There are no comments yet.


page 16


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...

Phase Transition for Support Recovery from Gaussian Linear Measurements

We study the problem of recovering the common k-sized support of a set o...

Tight Measurement Bounds for Exact Recovery of Structured Sparse Signals

Standard compressive sensing results state that to exactly recover an s ...

Error-Correction for Sparse Support Recovery Algorithms

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

Optimal sampling and assay for soil organic carbon estimation

The world needs around 150 Pg of negative carbon emissions to mitigate c...

Randomly Aggregated Least Squares for Support Recovery

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

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.