Piecewise linear regularized solution paths
From MaRDI portal
Publication:2642739
Abstract: We consider the generic regularized optimization problem . Efron, Hastie, Johnstone and Tibshirani [Ann. Statist. 32 (2004) 407--499] have shown that for the LASSO--that is, if is squared error loss and is the norm of --the optimal coefficient path is piecewise linear, that is, is piecewise constant. We derive a general characterization of the properties of (loss , penalty ) pairs which give piecewise linear coefficient paths. Such pairs allow for efficient generation of the full regularized coefficient paths. We investigate the nature of efficient path following algorithms which arise. We use our results to suggest robust versions of the LASSO for regression and classification, and to develop new, efficient algorithms for existing problems in the literature, including Mammen and van de Geer's locally adaptive regression splines.
Recommendations
- Piecewise-linear pathways to the optimal solution set in linear programming
- Piecewise linear solution paths with application to direct weight optimization
- Piecewise linear methods for nonlinear equations and optimization
- Piecewise-linearized methods for initial-value problems
- On the structure of regularization paths for piecewise differentiable regularization terms
- Iterative Solution of Piecewise Linear Systems
- Direct solution of piecewise linear systems
- Path-Following Methods for Linear Programming
- A regularized simplex method
- scientific article; zbMATH DE number 7038944
Cites work
- Boosting as a regularized path to a maximum margin classifier
- scientific article; zbMATH DE number 5957245 (Why is no real title available?)
- scientific article; zbMATH DE number 739533 (Why is no real title available?)
- scientific article; zbMATH DE number 823069 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Least angle regression. (With discussion)
- Local extremes, runs, strings and multiresolution. (With discussion)
- Locally adaptive regression splines
- Nonconcave penalized likelihood with a diverging number of parameters.
- On ψ-Learning
- Quantile regression.
- Quantile smoothing splines
- Ridge Regression: Biased Estimation for Nonorthogonal Problems
- Robust Estimation of a Location Parameter
- Sparsity and Smoothness Via the Fused Lasso
- The elements of statistical learning. Data mining, inference, and prediction
- Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
Cited in
(only showing first 100 items - show all)- The composite absolute penalties family for grouped and hierarchical variable selection
- SVM-Maj: a majorization approach to linear support vector machines with different hinge errors
- Nearly unbiased variable selection under minimax concave penalty
- Estimating the dimension of a model
- Estimation of high-dimensional graphical models using regularized score matching
- A modified local quadratic approximation algorithm for penalized optimization problems
- Robust methods for inferring sparse network structures
- Moderately clipped Lasso
- The dual and degrees of freedom of linearly constrained generalized Lasso
- A doubly sparse approach for group variable selection
- LARS-type algorithm for group Lasso
- Uniformly valid confidence sets based on the Lasso
- Least angle regression. (With discussion)
- Multi-parametric solution-path algorithm for instance-weighted support vector machines
- Dimension reduction and variable selection in case control studies via regularized likelihood optimization
- Majorization-minimization algorithms for nonsmoothly penalized objective functions
- The smooth-Lasso and other \(\ell _{1}+\ell _{2}\)-penalized methods
- Generalized \(\ell_1\)-penalized quantile regression with linear constraints
- Solution paths for the generalized Lasso with applications to spatially varying coefficients regression
- Machine learning subsurface flow equations from data
- Asymptotic linear expansion of regularized M-estimators
- Robust subset selection
- Conditional selective inference for robust regression and outlier detection using piecewise-linear homotopy continuation
- LASSO for streaming data with adaptative filtering
- Aggregated hold out for sparse linear regression with a robust loss function
- Adaptive multi-penalty regularization based on a generalized Lasso path
- A regularization path algorithm for support vector ordinal regression
- Estimating piecewise monotone signals
- Primal path algorithm for compositional data analysis
- Shrinkage estimation and variable selection in multiple regression models with random coefficient autoregressive errors
- A simple and efficient algorithm for fused lasso signal approximator with convex loss function
- An efficient algorithm for structured sparse quantile regression
- Post-Pareto analysis and a new algorithm for the optimal parameter tuning of the elastic net
- Novel harmonic regularization approach for variable selection in Cox's proportional hazards model
- Piecewise linear solution paths with application to direct weight optimization
- Solution path for quantile regression with epsilon-insensitive loss in a reproducing kernel Hilbert space
- Forward and backward least angle regression for nonlinear system identification
- Learning and estimation applications of an online homotopy algorithm for a generalization of the LASSO
- Adaptive piecewise polynomial estimation via trend filtering
- Pathwise coordinate optimization
- A sparse large margin semi-supervised learning method
- Regularization of case-specific parameters for robustness and efficiency
- On the structure of regularization paths for piecewise differentiable regularization terms
- Generalized methods and solvers for noise removal from piecewise constant signals. I: Background theory
- Generalized methods and solvers for noise removal from piecewise constant signals. II: New methods
- Splines for financial volatility
- A note on application of Nesterov's method in solving lasso-type problems
- Inference of genetic networks from time course expression data using functional regression with lasso penalty
- An ordinary differential equation-based solution path algorithm
- Efficient global approximation of generalized nonlinear \(\ell _{1}\)-regularized solution paths and its applications
- Weak convergence of the regularization path in penalized M-estimation
- The Dantzig Selector in Cox's Proportional Hazards Model
- Estimating spatial covariance using penalised likelihood with weightedL1penalty
- Algorithms for Fitting the Constrained Lasso
- Dynamic Visualization and Fast Computation for Convex Clustering via Algorithmic Regularization
- DASSO: Connections Between the Dantzig Selector and Lasso
- Quadratic approximation on SCAD penalized estimation
- On the optimality of averaging in distributed statistical learning
- Does modeling lead to more accurate classification? A study of relative efficiency in linear classification
- A sharp nonasymptotic bound and phase diagram of \(L_{1/2}\) regularization
- Optimal computational and statistical rates of convergence for sparse nonconvex learning problems
- Approximate penalization path for smoothly clipped absolute deviation
- Robust regression for highly corrupted response by shifting outliers
- A generic path algorithm for regularized statistical estimation
- Robust sparse regression by modeling noise as a mixture of Gaussians
- Structured sparse support vector machine with ordered features
- Penalized B-spline estimator for regression functions using total variation penalty
- An algorithmic view of _2 regularization and some path-following algorithms
- Statistical guarantees for local graph clustering
- Solution paths of variational regularization methods for inverse problems
- Paths Following Algorithm for Penalized Logistic Regression Using SCAD and MCP
- ℓ1 Regularization in Infinite Dimensional Feature Spaces
- Simultaneous Regression Shrinkage, Variable Selection, and Supervised Clustering of Predictors with OSCAR
- ``FISTA in Banach spaces with adaptive discretisations
- Accelerate the warm-up stage in the Lasso computation via a homotopic approach
- Comparing solution paths of sparse quadratic minimization with a Stieltjes matrix
- \(L_1\)-penalized fraud detection support vector machines
- The solution path of the generalized lasso
- Regularization paths of \(L_1\)-penalized ROC curve-optimizing support vector machines
- A confidence machine for sparse high-order interaction model
- Path-following methods for maximum a posteriori estimators in Bayesian hierarchical models: how estimates depend on hyperparameters
- Weight bound constraints in mean-variance models: a robust control theory foundation via machine learning
- A survey of numerical algorithms that can solve the Lasso problems
- Variable selection using \(L_q\) penalties
- Variable selection using P-splines
- Convex Bidirectional Large Margin Classifiers
- Predictive signature development based on maximizing the area between receiver operating characteristic curves
- Ranking Features to Promote Diversity: An Approach Based on Sparse Distance Correlation
- Bootstrap estimation of the proportion of outliers in robust regression
- A unified and efficient proximal gradient descent algorithm for penalized convoluted support vector machines
- Heavy Lasso: sparse penalized regression under heavy-tailed noise via data-augmented soft-thresholding
- Lasso Monte Carlo, a variation on multi fidelity methods for high-dimensional uncertainty quantification
- New methods for parametric optimization via differential equations
- A unified consensus-based parallel algorithm for high-dimensional regression with combined regularizations
- Parallel ADMM algorithm with Gaussian back substitution for high-dimensional quantile regression and classification
- Tutorial in biostatistics: data-driven subgroup identification and analysis in clinical trials
- Robust quantile regression in RKHS: solution paths for censored and truncated data
- Efficient Distributed Learning over Decentralized Networks with Convoluted Support Vector Machine
- Convoluted support matrix machine in high dimensions
- Integrative learning of individualized treatment rules from multiple studies with partially overlapping treatments
This page was built for publication: Piecewise linear regularized solution paths
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2642739)
