Model selection for high-dimensional quadratic regression via regularization
From MaRDI portal
Abstract: Quadratic regression (QR) models naturally extend linear models by considering interaction effects between the covariates. To conduct model selection in QR, it is important to maintain the hierarchical model structure between main effects and interaction effects. Existing regularization methods generally achieve this goal by solving complex optimization problems, which usually demands high computational cost and hence are not feasible for high dimensional data. This paper focuses on scalable regularization methods for model selection in high dimensional QR. We first consider two-stage regularization methods and establish theoretical properties of the two-stage LASSO. Then, a new regularization method, called Regularization Algorithm under Marginality Principle (RAMP), is proposed to compute a hierarchy-preserving regularization solution path efficiently. Both methods are further extended to solve generalized QR models. Numerical results are also shown to demonstrate performance of the methods.
Recommendations
- Variable selection in sparse regression with quadratic measurements
- Penalized interaction estimation for ultrahigh dimensional quadratic regression
- Regularized simultaneous model selection in multiple quantiles regression
- A systematic review on model selection in high-dimensional regression
- FSR methods for second-order regression models
Cites work
- L 1-Regularization Path Algorithm for Generalized Linear Models
- A Bayesian Variable-Selection Approach for Analyzing Designed Experiments with Complex Aliasing
- A generic path algorithm for regularized statistical estimation
- A lasso for hierarchical interactions
- A Note on High-Dimensional Linear Regression With Interactions
- An ordinary differential equation-based solution path algorithm
- APPLE: approximate path for penalized likelihood estimators
- Asymptotic Equivalence of Regularization Methods in Thresholded Parameter Space
- Coordinate descent algorithms for lasso penalized regression
- Extended Bayesian information criteria for model selection with large model spaces
- Forward regression for ultra-high dimensional variable screening
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Innovated interaction screening for high-dimensional nonlinear classification
- Interaction pursuit in high-dimensional multi-response regression via distance correlation
- Interaction screening for ultrahigh-dimensional data
- Least angle regression. (With discussion)
- Nearly unbiased variable selection under minimax concave penalty
- Nonconcave Penalized Likelihood With NP-Dimensionality
- Nonparametric independence screening and structure identification for ultra-high dimensional longitudinal data
- Nonparametric independence screening in sparse ultra-high-dimensional additive models
- Pathwise coordinate optimization
- Regularization and Variable Selection Via the Elastic Net
- Sharp Thresholds for High-Dimensional and Noisy Sparsity Recovery Using $\ell _{1}$-Constrained Quadratic Programming (Lasso)
- Structured variable selection and estimation
- Sure independence screening for ultrahigh dimensional feature space. With discussion and authors' reply
- The composite absolute penalties family for grouped and hierarchical variable selection
- Tuning parameter selection in high dimensional penalized likelihood
- Variable selection for general index models via sliced inverse regression
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
- Variable selection with the strong heredity constraint and its oracle property
Cited in
(48)- A two-stage regularization method for variable selection and forecasting in high-order interaction model
- Identifying main effects and interactions among exposures using Gaussian processes
- Variable selection for functional linear models with strong heredity constraint
- Estimating the health effects of environmental mixtures using Bayesian semiparametric regression and sparsity inducing priors
- Model selection for functional linear regression with hierarchical structure
- Variable selection in sparse regression with quadratic measurements
- High-dimensional interactions detection with sparse principal Hessian matrix
- Sequential interaction group selection by the principle of correlation search for high-dimensional interaction models
- RaSE: random subspace ensemble classification
- Partitioned Approach for High-dimensional Confidence Intervals with Large Split Sizes
- Efficient kernel-based variable selection with sparsistency
- Automatic variable selection in a linear model on massive data
- Nonparametric Interaction Selection
- Penalized interaction estimation for ultrahigh dimensional quadratic regression
- Layer-wise learning strategy for nonparametric tensor product smoothing spline regression and graphical models
- High-dimensional statistical inference via DATE
- A Note on High-Dimensional Linear Regression With Interactions
- Bayesian Factor Analysis for Inference on Interactions
- Two-Level Bayesian Interaction Analysis for Survival Data Incorporating Pathway Information
- BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data
- High-Dimensional Gaussian Graphical Regression Models with Covariates
- Bayesian Interaction Selection Model for Multimodal Neuroimaging Data Analysis
- Sparse and Low-Rank Matrix Quantile Estimation With Application to Quadratic Regression
- Ranked sparsity: a cogent regularization framework for selecting and estimating feature interactions and polynomials
- A sparse additive model for high-dimensional interactions with an exposure variable
- A General Framework for Identifying Hierarchical Interactions and Its Application to Genomics Data
- Structure learning via unstructured kernel-based M-estimation
- Nested model averaging on solution path for high-dimensional linear regression
- HiQR: an efficient algorithm for high-dimensional quadratic regression with penalties
- Detecting clusters in multivariate response regression
- An efficient model-free approach to interaction screening for high dimensional data
- High-Dimensional Interaction Detection With False Sign Rate Control
- Variable selection for high-dimensional partly linear additive Cox model with application to Alzheimer's disease
- Gene-gene interaction analysis incorporating network information via a structured Bayesian approach
- Nonparametric feature screening for interaction effects in ultrahigh-dimensional survival data
- Variable selection for high-dimensional quadratic Cox model with application to Alzheimer's disease
- Interaction screening in high-dimensional multi-response regression via projected distance correlation
- Sparsified simultaneous confidence intervals for high-dimensional linear models
- Low-rank longitudinal factor regression with application to chemical mixtures
- Inferring synergistic and antagonistic interactions in mixtures of exposures
- On Exact Feature Screening in Ultrahigh-Dimensional Binary Classification
- Forward selection and post-selection inference in factorial designs
- Model selection based on KL divergence with censoring indicators missing at random
- Conditional variable screening for ultra-high dimensional longitudinal data with time interactions
- Variable importance based interaction modelling with an application on initial spread of COVID-19 in China
- Tensor-on-vector regression with interactions with application to fMRI data
- GMI: group-level main effects and interactions in high-dimensional data with applications to pathway and interaction discovery in gene expression analysis
- Examining the feasibility of quadratic vector autoregressions for psychological intensive longitudinal data
This page was built for publication: Model selection for high-dimensional quadratic regression via regularization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4962427)
