Abstract
In this note, the notion of admissible sets contained in the strictly positive orthant introduced in Micchelli et al. (Adv. Comp. Math. 38(3), 455–489 2013) is analyzed. This notion was used to generalize theoretical results and optimization methods for structured sparsity. Unfortunately, we will prove that there is no generalization using admissible sets.
Similar content being viewed by others
References
Combettes, P.L.: Perspective functions: properties, constructions, and examples. Set-Valued Var. Anal (2017). https://doi.org/10.1007/s11228-017-0407-x
Maurer, A., Pontil, M.: Structured sparsity and generalization. J. Mach. Learn. Res. 13, 671–690 (2012)
McDonald, A., Pontil, M., Stamos, D.: New perspectives on k-support and cluster norms. J. Mach. Learn. Res. 17, 38 (2016)
Micchelli, C.A., Morales, J.M., Pontil, M.: A family of penalty functions for structured sparsity. In: Lafferty, J., et al. (eds.) Advance in Neural Information Proceedings System, vol. 23, pp. 1612–1623 (2010)
Micchelli, C.A., Morales, J.M., Pontil, M.: Reguralizers for structured sparsity. Adv. Comp. Math. 38(3), 455–489 (2013)
Sankaran, R., Bach, F., Bhattacharya, C.: Identifying groups of strongly correlated variables through smoothed ordered weighted ℓ 1-norms. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR, vol. 54, pp. 1123–1131 (2017)
Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc., B Stat. Methodol. 58(1), 267–288 (1996)
van de Geer, S.: Structured sparsity. In: Estimation and Testing Under Sparsity. Lecture Notes in Mathematics, vol. 2159, pp. 75–101 (2016)
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by: Tomas Sauer
This research was partially supported by Conicyt–Chile under project Fondecyt Postdoctorado 3160205.
Rights and permissions
About this article
Cite this article
Lara, F. A note on “Reguralizers for structured sparsity”. Adv Comput Math 44, 1321–1323 (2018). https://doi.org/10.1007/s10444-017-9583-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10444-017-9583-3