Sparse Poisson regression with penalized weighted score function

DOI10.1214/19-EJS1580zbMATH Open1431.62300arXiv1703.03965OpenAlexW2970191091MaRDI QIDQ2323944FDOQ2323944

Authors: Jinzhu Jia, Fang Xie, Lihu Xu 

Publication date: 13 September 2019

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Abstract: We proposed a new penalized method in this paper to solve sparse Poisson Regression problems. Being different from $el{l}_1$ penalized log-likelihood estimation, our new method can be viewed as penalized weighted score function method. We show that under mild conditions, our estimator is $el{l}_1$ consistent and the tuning parameter can be pre-specified, which shares the same good property of the square-root Lasso.

Full work available at URL: https://arxiv.org/abs/1703.03965

Recommendations

• A consistent and numerically efficient variable selection method for sparse Poisson regression with applications to learning and signal recovery
• An estimation method for high dimension Poisson regression models
• Adaptive Lasso and group-Lasso for functional Poisson regression
• The adaptive Lasso in high-dimensional sparse heteroscedastic models
• The lasso under Poisson-like heteroscedasticity

zbMATH Keywords

Poisson regressionimage reconstructionsquare root Lassotuning-free

Mathematics Subject Classification ID

Statistical aspects of big data and data science (62R07) Ridge regression; shrinkage estimators (Lasso) (62J07) Image analysis in multivariate analysis (62H35)

Cites Work

• Nearly unbiased variable selection under minimax concave penalty
• The Adaptive Lasso and Its Oracle Properties
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Title not available (Why is that?)
• Simultaneous analysis of Lasso and Dantzig selector
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• On asymptotically optimal confidence regions and tests for high-dimensional models
• Title not available (Why is that?)
• High-dimensional Ising model selection using \(\ell _{1}\)-regularized logistic regression
• Title not available (Why is that?)
• On model selection consistency of regularized M-estimators
• Nonconcave Penalized Likelihood With NP-Dimensionality
• Self-concordant analysis for logistic regression
• Compressed Sensing Performance Bounds Under Poisson Noise
• Self-normalized Cramér type moderate deviations for the maximum of sums
• Non-Uniform Estimates, Moderate and Large Deviations in the Central Limit Theorem form-Dependent Random Variables
• Berry-Esseen type estimates for large deviation probabilities
• Adaptive Lasso and group-Lasso for functional Poisson regression

Cited In (7)

• Title not available (Why is that?)
• Oracle inequalities for weighted group Lasso in high-dimensional Poisson regression model
• Estimating a regression function in exponential families by model selection
• Weak Signal Identification and Inference in Penalized Likelihood Models for Categorical Responses
• Consistency of \(\ell_1\) penalized negative binomial regressions
• A New Homotopy Proximal Variable-Metric Framework for Composite Convex Minimization
• Title not available (Why is that?)

This page was built for publication: Sparse Poisson regression with penalized weighted score function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2323944)