Sparse regularization via bidualization

Amir Beck*, Yehonathan Refael

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The paper considers the sparse envelope function, defined as the biconjugate of the sum of a squared ℓ2-norm function and the indicator of the set of k-sparse vectors. It is shown that both function and proximal values of the sparse envelope function can be reduced into a one-dimensional search that can be efficiently performed in linear time complexity in expectation. The sparse envelope function naturally serves as a regularizer that can handle both sparsity and grouping information in inverse problems, and can also be utilized in sparse support vector machine problems.

Original languageEnglish
Pages (from-to)463-482
Number of pages20
JournalJournal of Global Optimization
Volume82
Issue number3
DOIs
StatePublished - Mar 2022

Funding

FundersFunder number
Israel Science Foundation92621
Israel Science Foundation

    Keywords

    • Biconjugate
    • Convex envelope
    • Randomized root search
    • Sparsity

    Fingerprint

    Dive into the research topics of 'Sparse regularization via bidualization'. Together they form a unique fingerprint.

    Cite this