Scaling law for recovering the sparsest element in a subspace
We address the problem of recovering a sparse n-vector within a given subspace. This problem is a subtask of some approaches to dictionary learning and sparse principal component analysis. Hence, if we can prove scaling laws for recovery of sparse vectors, it will be easier to derive and prove recov...
Main Authors: | Demanet, Laurent, Hand, Paul |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Mathematics |
Format: | Article |
Published: |
Oxford University Press (OUP)
2018
|
Online Access: | http://hdl.handle.net/1721.1/115483 https://orcid.org/0000-0001-7052-5097 |
Similar Items
-
Sparse Representations Are Most Likely to Be the Sparsest Possible
by: Elad Michael
Published: (2006-01-01) -
Learning directed acyclic graph models based on sparsest permutations
by: Raskutti, Garvesh, et al.
Published: (2021) -
Stable Optimizationless Recovery from Phaseless Linear Measurements
by: Demanet, Laurent, et al.
Published: (2015) -
Feedforward control, PID control laws, and almost invariant subspaces
Published: (2002) -
Convergence of restarted Krylov subspaces to invariant subspaces
by: Beattie, C, et al.
Published: (2001)