Lasso in Infinite dimension: application to variable selection in functional multivariate linear regression
From MaRDI portal
Abstract: It is more and more frequently the case in applications that the data we observe come from one or more random variables taking values in an infinite dimensional space, e.g. curves. The need to have tools adapted to the nature of these data explains the growing interest in the field of functional data analysis. The model we study in this paper assumes a linear dependence between a quantity of interest and several covariates, at least one of which has an infinite dimension. To select the relevant covariates in this context, we investigate adaptations of the Lasso method. Two estimation methods are defined. The first one consists in the minimization of a Group-Lasso criterion on the multivariate functional space H. The second one minimizes the same criterion but on a finite dimensional subspaces of H whose dimension is chosen by a penalized least squares method. We prove oracle inequalities of sparsity in the case where the design is fixed or random. To compute the solutions of both criteria in practice, we propose a coordinate descent algorithm. A numerical study on simulated and real data illustrates the behavior of the estimators.
Cites work
- scientific article; zbMATH DE number 6388313 (Why is no real title available?)
- scientific article; zbMATH DE number 5828468 (Why is no real title available?)
- scientific article; zbMATH DE number 3518130 (Why is no real title available?)
- scientific article; zbMATH DE number 469124 (Why is no real title available?)
- scientific article; zbMATH DE number 2015204 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- A Data-Dependent Weighted LASSO Under Poisson Noise
- A fast unified algorithm for solving group-lasso penalize learning problems
- Adaptive Dantzig density estimation
- Adaptive Lasso and group-Lasso for functional Poisson regression
- Adaptive estimation in circular functional linear models
- Adaptive estimation in the functional nonparametric regression model
- Adaptive functional linear regression
- An introduction to recent advances in high/infinite dimensional statistics
- Asymptotic properties of Lasso+mLS and Lasso+Ridge in sparse high-dimensional linear regression
- Atomic decomposition by basis pursuit
- Bayesian functional linear regression with sparse step functions
- Bounds on the prediction error of penalized least squares estimators with convex penalty
- CLT in functional linear regression models
- Component selection and smoothing in multivariate nonparametric regression
- Consistency of the group Lasso and multiple kernel learning
- Curse of dimensionality and related issues in nonparametric functional regression
- Dimension fractale et estimation de la régression dans des espaces vectoriels semi-normés
- Dynamic functional data analysis with non-parametric state space models
- Estimation and inference in partially functional linear regression with multiple functional covariates
- Functional data analysis.
- Functional linear model
- Functional linear regression that's interpretable
- Group Lasso for structural break time series
- High-dimensional principal projections
- Introduction to nonparametric estimation
- Linear processes in function spaces. Theory and applications
- Local optimization of black-box functions with high or infinite-dimensional inputs: application to nuclear safety
- Lower bound in regression for functional data by representation of small ball probabilities
- Model Selection and Estimation in Regression with Grouped Variables
- Model selection for regression on a fixed design
- Model-based regression clustering for high-dimensional data: application to functional data
- Multilevel functional principal component analysis
- Multivariate functional linear regression and prediction
- Multivariate functional principal component analysis: A normalization approach
- Non-asymptotic adaptive prediction in functional linear models
- Non-asymptotic oracle inequalities for the Lasso and group Lasso in high dimensional logistic model
- Nonparametric functional data analysis. Theory and practice.
- Nonparametric modelling for functional data: selected survey and tracks for future
- On prediction rate in partial functional linear regression
- On rates of convergence in functional linear regression
- On the asymptotic properties of the group lasso estimator for linear models
- On the conditions used to prove oracle results for the Lasso
- Optimal prediction for high-dimensional functional quantile regression in reproducing kernel Hilbert spaces
- Oracle Inequalities for a Group Lasso Procedure Applied to Generalized Linear Models in High Dimension
- Oracle inequalities and optimal inference under group sparsity
- PLS regression on a stochastic process
- Partial functional linear regression
- Partially Linear Functional Additive Models for Multivariate Functional Data
- Partially functional linear regression in high dimensions
- Quantification of symmetry for functional data with application to equine lameness classification
- Risk bounds for model selection via penalization
- Shrinkage estimation and selection for multiple functional regression
- Simultaneous analysis of Lasso and Dantzig selector
- Slope heuristics: overview and implementation
- Slope meets Lasso: improved oracle bounds and optimality
- Smoothing splines estimators for functional linear regression
- Some theoretical results on the grouped variables Lasso
- Sparse nonparametric model for regression with functional covariate
- Sparse semiparametric regression when predictors are mixture of functional and high-dimensional variables
- Sparsity oracle inequalities for the Lasso
- Structure-leveraged methods in breast cancer risk prediction
- The Dantzig selector and sparsity oracle inequalities
- The Group Lasso for Logistic Regression
- The benefit of group sparsity
- The role of statistics in the era of big data
- Thresholding projection estimators in functional linear models
- Tuning parameter selectors for the smoothly clipped absolute deviation method
- Unified LASSO Estimation by Least Squares Approximation
- Variable selection in infinite-dimensional problems
- Weakly decomposable regularization penalties and structured sparsity
- \(L_1\)-penalization in functional linear regression with subgaussian design
This page was built for publication: Lasso in Infinite dimension: application to variable selection in functional multivariate linear regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144429)
