Back to Search
Start Over
On the Sparsity of LASSO Minimizers in Sparse Data Recovery.
- Source :
-
Constructive Approximation . Apr2023, Vol. 57 Issue 2, p901-919. 19p. - Publication Year :
- 2023
-
Abstract
- We present a detailed analysis of the unconstrained ℓ 1 -weighted LASSO method for recovery of sparse data from its observation by randomly generated matrices, satisfying the restricted isometry property (RIP) with constant δ < 1 , and subject to negligible measurement and compressibility errors. We prove that if the data are k-sparse, then the size of support of the LASSO minimizer, s, maintains a comparable sparsity, s ⩽ C δ k . For example, if δ = 0.7 then s < 11 k and a slightly smaller δ = 0.4 yields s < 4 k . We also derive new ℓ 2 / ℓ 1 error bounds which highlight precise dependence on k and on the LASSO parameter λ , before the error is driven below the scale of negligible measurement/ and compressiblity errors. [ABSTRACT FROM AUTHOR]
- Subjects :
- *DATA recovery
*RESTRICTED isometry property
*MEASUREMENT errors
Subjects
Details
- Language :
- English
- ISSN :
- 01764276
- Volume :
- 57
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Constructive Approximation
- Publication Type :
- Academic Journal
- Accession number :
- 163189129
- Full Text :
- https://doi.org/10.1007/s00365-022-09594-1