Elastic-net regularization versus $\ell^1$-regularization for linear inverse problems with quasi-sparse solutions
De-Han Chen, Bernd Hofmann, Jun Zou

TL;DR
This paper compares elastic-net and $ ext{l}^1$-regularization for solving ill-posed linear inverse problems with quasi-sparse solutions, analyzing convergence rates based on solution decay and smoothness.
Contribution
It provides a theoretical analysis of elastic-net regularization, including convergence rate estimates, under assumptions on solution decay and smoothness, extending prior work on $ ext{l}^1$-regularization.
Findings
Elastic-net regularization converges under certain decay and smoothness conditions.
The convergence rate depends on the decay rate of solution coefficients and smoothness properties.
The analysis includes the influence of two parameters: the weight and regularization parameters.
Abstract
We consider the ill-posed operator equation with an injective and bounded linear operator mapping between and a Hilbert space , possessing the unique solution \linebreak . For the cases that sparsity is expected but often slightly violated in practice, we investigate in comparison with the -regularization the elastic-net regularization, where the penalty is a weighted superposition of the -norm and the -norm square, under the assumption that . There occur two positive parameters in this approach, the weight parameter and the regularization parameter as the multiplier of the whole penalty in the Tikhonov functional, whereas only one regularization parameter arises in -regularization. Based on the variational inequality approach for the description of the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
