Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Accelerating Non-Negative and Bounded-Variable Linear Regression Algorithms with Safe Screening

Abstract : Non-negative and bounded-variable linear regression problems arise in a variety of applications in machine learning and signal processing. In this paper, we propose a technique to accelerate existing solvers for these problems by identifying saturated coordinates in the course of iterations. This is akin to safe screening techniques previously proposed for sparsity-regularized regression problems. The proposed strategy is provably safe as it provides theoretical guarantees that the identified coordinates are indeed saturated in the optimal solution. Experimental results on synthetic and real data show compelling accelerations for both non-negative and bounded-variable problems.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03564336
Contributor : Cassio F. Dantas Connect in order to contact the contributor
Submitted on : Friday, February 11, 2022 - 2:11:02 PM
Last modification on : Friday, August 5, 2022 - 10:51:50 AM

Files

NN-BV_Screening_v1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03564336, version 1
  • ARXIV : 2202.07258

Citation

Cassio F. Dantas, Emmanuel Soubies, Cédric Févotte. Accelerating Non-Negative and Bounded-Variable Linear Regression Algorithms with Safe Screening. 2022. ⟨hal-03564336⟩

Share

Metrics

Record views

102

Files downloads

17