A Computational Framework for Multivariate Convex Regression and Its Variants
From MaRDI portal
Publication:5229914
Abstract: We study the nonparametric least squares estimator (LSE) of a multivariate convex regression function. The LSE, given as the solution to a quadratic program with linear constraints ( being the sample size), is difficult to compute for large problems. Exploiting problem specific structure, we propose a scalable algorithmic framework based on the augmented Lagrangian method to compute the LSE. We develop a novel approach to obtain smooth convex approximations to the fitted (piecewise affine) convex LSE and provide formal bounds on the quality of approximation. When the number of samples is not too large compared to the dimension of the predictor, we propose a regularization scheme --- Lipschitz convex regression --- where we constrain the norm of the subgradients, and study the rates of convergence of the obtained LSE. Our algorithmic framework is simple and flexible and can be easily adapted to handle variants: estimation of a non-decreasing/non-increasing convex/concave (with or without a Lipschitz bound) function. We perform numerical studies illustrating the scalability of the proposed algorithm.
Recommendations
- An augmented Lagrangian method with constraint generation for shape-constrained convex regression problems
- Nonparametric least squares estimation of a multivariate convex regression function
- Consistency of multidimensional convex regression
- Multivariate convex regression with adaptive partitioning
- On convergence rates of convex regression in multiple dimensions
Cites work
- A finite algorithm for finding the projection of a point onto the canonical simplex of \({\mathbb R}^ n\)
- A first-order augmented Lagrangian method for compressed sensing
- An Empirical Distribution Function for Sampling with Incomplete Information
- Consistency of multidimensional convex regression
- Consistent estimation of a convex density at the origin
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Estimating a Convex Function in Nonparametric Regression
- Estimating a smooth monotone regression function
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 1862807 (Why is no real title available?)
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 1420699 (Why is no real title available?)
- Introductory lectures on convex optimization. A basic course.
- Lectures on Stochastic Programming
- Maximum Likelihood Estimates of Monotone Parameters
- Maximum likelihood estimation of a multi-dimensional log-concave density. With discussion and authors' reply
- Monotone nonparametric regression
- Multivariate convex regression with adaptive partitioning
- Nonparametic kernel regression with multiple predictors and multiple shape constraints
- Nonparametric estimation of multivariate convex-transformed densities
- Nonparametric least squares estimation of a multivariate convex regression function
- On convergence rates of convex regression in multiple dimensions
- On the linear convergence of the alternating direction method of multipliers
- On uniform consistent estimators for convex regression
- Representation theorem for convex nonparametric least squares
- Smooth minimization of non-smooth functions
- The direct extension of ADMM for multi-block convex minimization problems is not necessarily convergent
- The Nonparametric Approach to Demand Analysis
- The Nonparametric Approach to Production Analysis
Cited in
(33)- Editorial: Special issue on ``Nonparametric inference under shape constraints
- Shape constraints in economics and operations research
- Nonparametric shape-restricted regression
- A penalized method for multivariate concave least squares with application to productivity analysis
- Variable selection in convex quantile regression: \(\mathcal{L}_1\)-norm or \(\mathcal{L}_0\)-norm regularization?
- Stratified incomplete local simplex tests for curvature of nonparametric multiple regression
- An augmented Lagrangian method with constraint generation for shape-constrained convex regression problems
- Center-outward quantiles and the measurement of multivariate risk
- A more efficient algorithm for convex nonparametric least squares
- Adaptation in multivariate log-concave density estimation
- Consistency of multidimensional convex regression
- Multivariate convex regression with adaptive partitioning
- On convergence rates of convex regression in multiple dimensions
- scientific article; zbMATH DE number 6617259 (Why is no real title available?)
- Representation theorem for convex nonparametric least squares
- Composite difference-MAX programs for modern statistical estimation problems
- Sparse Convex Regression
- A User-Friendly Computational Framework for Robust Structured Regression with the L2 Criterion
- A dual active set algorithm for optimal sparse convex regression
- Assessing Panamanian hospitals' performance with alternative frontier methods
- Performance enhancements for a generic conic interior point algorithm
- Semiparametric Efficiency in Convexity Constrained Single-Index Model
- Spectrahedral Regression
- Generalized quantile and expectile properties for shape constrained nonparametric estimation
- Convex support vector regression
- Subgradient regularized multivariate convex regression at scale
- Plugin estimation of smooth optimal transport maps
- Convergence rates for estimating multivariate scale mixtures of uniform densities
- Structure identification for partially linear partially concave models
- Convex regression in multidimensions: suboptimality of least squares estimators
- A two-level method for constructing linear regressions using optimal convex combinations
- Boundary problem and overfitting reduction in convex regression
- Sparse convex quantile regression: a generalized Benders decomposition approach
This page was built for publication: A Computational Framework for Multivariate Convex Regression and Its Variants
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5229914)
