Metraipolis › archive › dc_f7a261d10e7e

Convex Reparameterization and Self-Concordant Algorithms for Multivariate Regression with Covariance Estimation — arXiv:2608.18441

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18441
License (as archived)
CC0-1.0
Archived
2026-10-18T13:56:55.695Z
SHA-256 of the archived text
1590e8aa0b21994c9a5082d12c16cf5d19cea80cdd6a2caff7cbedcfca749bbe
Stable URL of this page
https://metraipolis.com/documento/dc_f7a261d10e7e

How to cite

Convex Reparameterization and Self-Concordant Algorithms for Multivariate Regression with Covariance Estimation — arXiv:2608.18441 — arXiv (en), https://arxiv.org/abs/2608.18441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f7a261d10e7e (Metraipolis archive dc_f7a261d10e7e, sha256 1590e8aa0b21994c9a5082d12c16cf5d19cea80cdd6a2caff7cbedcfca749bbe)
BibTeX
@misc{dcf7a261d10e7e,
  title = {Convex Reparameterization and Self-Concordant Algorithms for Multivariate Regression with Covariance Estimation — arXiv:2608.18441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f7a261d10e7e; sha256 1590e8aa0b21994c9a5082d12c16cf5d19cea80cdd6a2caff7cbedcfca749bbe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Building on a reparameterization for multivariate linear regression that yields a jointly convex penalized likelihood in the reparameterized regression coefficient matrix and the precision matrix, we show that the resulting scaled Gaussian loss is standard self-concordant. This places the joint estimation problem within composite self-concordant optimization and leads to two algorithms: a proximal gradient method and a damped proximal Newton method. In simulations, we evaluate algorithmic robustness, iterations to convergence, and elapsed time. In a protein expression application, compared with the classical-parameterization formulation, the proposed convex formulation attains similar mean squared prediction error and can be substantially faster when the fitted precision matrix is dense.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in stat.ME).
Categorie arXiv: Computation (stat.CO) ; Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.18441 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T13:53:24.418Z dalla pagina https://arxiv.org/catchup/stat.ME/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).