Mixtures, envelopes and hierarchical duality
From MaRDI portal
(Redirected from Publication:5378366)
Bayesian inferenceconvex dualityenvelopesGaussian mixturesmaximum \textit{a posteriori} estimationpenalized likelihoodvariational methods
Software, source code, etc. for problems pertaining to statistics (62-04) Minimax procedures in statistical decision theory (62C20) Statistical distribution theory (62Exx) Point estimation (62F10) Bayesian inference (62F15) Nonparametric estimation (62G05) Ridge regression; shrinkage estimators (Lasso) (62J07)
Abstract: We develop a connection between mixture and envelope representations of objective functions that arise frequently in statistics. We refer to this connection using the term "hierarchical duality." Our results suggest an interesting and previously under-exploited relationship between marginalization and profiling, or equivalently between the Fenchel--Moreau theorem for convex functions and the Bernstein--Widder theorem for Laplace transforms. We give several different sets of conditions under which such a duality result obtains. We then extend existing work on envelope representations in several ways, including novel generalizations to variance-mean models and to multivariate Gaussian location models. This turns out to provide an elegant missing-data interpretation of the proximal gradient method, a widely used algorithm in machine learning. We show several statistical applications in which the proposed framework leads to easily implemented algorithms, including a robust version of the fused lasso, nonlinear quantile regression via trend filtering, and the binomial fused double Pareto model. Code for the examples is available on GitHub at https://github.com/jgscott/hierduals.
Recommendations
- Proximal algorithms in statistics and machine learning
- Foundations for envelope models and methods
- Duality results and proximal solutions of the Huber M-estimator problem
- \(\ell_{1}\)-penalization for mixture regression models
- Unifying Divergence Minimization and Statistical Inference Via Convex Duality
Cited in
(6)- Proximal algorithms in statistics and machine learning
- The horseshoe-like regularization for feature subset selection
- Weighted Bayesian bootstrap for scalable posterior distributions
- Horseshoe Regularisation for Machine Learning in Complex and Deep Models1
- Bayesian \(l_0\)-regularized least squares
- Matching prior pairs connecting maximum a posteriori estimation and posterior expectation
This page was built for publication: Mixtures, envelopes and hierarchical duality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5378366)
