Ridge-Adding Approach for SVMpath Singularities

Autor: Binyu Wang, Lei Zhou, Zheng Cao, Jisheng Dai

Publikováno v: IEEE Access, Vol 7, Pp 47728-47736 (2019)

This paper introduces a novel ridge-adding approach for handling the singularity problem which is frequently encountered among the entire regularization path of support vector machine (SVM). Different from the existing ridge-adding method that direct

Externí odkaz: https://doaj.org/article/dea441785c8c4f4aa7cb67d77d481048

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Unbalanced Optimal Transport through Non-negative Penalized Linear Regression

Autor: Chapel, Laetitia, Flamary, Rémi, Wu, Haoran, Févotte, Cédric, Gasso, Gilles

Publikováno v: IEEE Transactions on Signal Processing
Advances in Neural Information Processing Systems (NeurIPS)
Advances in Neural Information Processing Systems (NeurIPS), Dec 2021, Online, France
Advances in Neural Information Processing Systems (NeurIPS), Dec 2021, Virtual, Canada

This paper addresses the problem of Unbalanced Optimal Transport (UOT) in which the marginal conditions are relaxed (using weighted penalties in lieu of equality) and no additional regularization is enforced on the OT plan. In this context, we show t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3ccdbea7fdefdef048732e8f1cefb3fb
https://hal.science/hal-03371489

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Regularization Paths for Generalized Linear Models via Coordinate Descent

Autor: Jerome Friedman, Trevor Hastie, Rob Tibshirani

Publikováno v: Journal of Statistical Software, Vol 33, Iss 01 (2010)

We develop fast algorithms for estimation of generalized linear models with convex penalties. The models include linear regression, two-class logistic regression, and multi- nomial regression problems while the penalties include ℓ1 (the lasso), ℓ

Externí odkaz: https://doaj.org/article/1204e8e8c9f9457e948a000727caaed7