Dimension reduction via Gaussian ridge functions
From MaRDI portal
Publication:4960976
DOI10.1137/18M1168571zbMATH Open1436.60038arXiv1802.00515WikidataQ126863788 ScholiaQ126863788MaRDI QIDQ4960976FDOQ4960976
Authors: Pranay Seshadri, Shaowu Yuchi, Geoffrey T. Parks 
Publication date: 24 April 2020
Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)
Abstract: Ridge functions have recently emerged as a powerful set of ideas for subspace-based dimension reduction. In this paper we begin by drawing parallels between ridge subspaces, sufficient dimension reduction and active subspaces, contrasting between techniques rooted in statistical regression and those rooted in approximation theory. This sets the stage for our new algorithm that approximates what we call a Gaussian ridge function---the posterior mean of a Gaussian process on a dimension-reducing subspace---suitable for both regression and approximation problems. To compute this subspace we develop an iterative algorithm that optimizes over the Stiefel manifold to compute the subspace, followed by an optimization of the hyperparameters of the Gaussian process. We demonstrate the utility of the algorithm on two analytical functions, where we obtain near exact ridge recovery, and a turbomachinery case study, where we compare the efficacy of our approach with three well-known sufficient dimension reduction methods: SIR, SAVE, CR. The comparisons motivate the use of the posterior variance as a heuristic for identifying the suitability of a dimension-reducing subspace.
Full work available at URL: https://arxiv.org/abs/1802.00515
Recommendations
- A near-stationary subspace for ridge approximation
- Gradient-based dimension reduction of multivariate vector-valued functions
- Active subspace methods in theory and practice: applications to kriging surfaces
- Approximation of generalized ridge functions in high dimensions
- Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments
dimension reductionGaussian process regressionsufficient dimension reductionactive subspacesmanifold optimization
Gaussian processes (60G15) Synthetic treatment of fundamental manifolds in projective geometries (Grassmannians, Veronesians and their generalizations) (51M35)
Cites Work
- Gaussian processes for machine learning (GPML) toolbox
- Manopt, a Matlab toolbox for optimization on manifolds
- Low-rank matrix completion via preconditioned optimization on the Grassmann manifold
- Gaussian processes for machine learning.
- Sliced Inverse Regression for Dimension Reduction
- The Geometry of Algorithms with Orthogonality Constraints
- Dimension Reduction for Gaussian Process Emulation: An Application to the Influence of Bathymetry on Tsunami Heights
- Title not available (Why is that?)
- Title not available (Why is that?)
- Gaussian processes with built-in dimensionality reduction: applications to high-dimensional uncertainty propagation
- On Directional Regression for Dimension Reduction
- Title not available (Why is that?)
- Sufficient dimension reduction and prediction in regression
- Sufficient Dimension Reduction via Inverse Regression
- Exploring Regression Structure Using Nonparametric Functional Estimation
- Save: a method for dimension reduction and graphics in regression
- Optimal Design of Experiments
- Optimization. Algorithms and consistent approximations
- Learning functions of few arbitrary linear parameters in high dimensions
- Learning non-parametric basis independent models from point queries via low-rank methods
- Rejoinder: Fisher lecture: Dimension reduction in regression
- Ridge functions
- The Elements of Statistical Learning
- Capturing ridge functions in high dimensions from point queries
- Title not available (Why is that?)
- Active subspaces. Emerging ideas for dimension reduction in parameter studies
- Discovering an active subspace in a single‐diode solar cell model
- Active subspace methods in theory and practice: applications to kriging surfaces
- A modified SEIR model for the spread of Ebola in western Africa and metrics for resource allocation
- A review on dimension reduction
- Stability analysis of thermo-acoustic nonlinear eigenproblems in annular combustors. Part II. Uncertainty quantification
- Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments
- A near-stationary subspace for ridge approximation
Cited In (11)
- A Hierarchical Expected Improvement Method for Bayesian Optimization
- Efficient reduced-rank methods for Gaussian processes with eigenfunction expansions
- Data-driven polynomial ridge approximation using variable projection
- Gradient-based dimension reduction of multivariate vector-valued functions
- Embedded ridge approximations
- Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments
- Gaussian quadrature and polynomial approximation for one-dimensional ridge functions
- Hierarchical shrinkage Gaussian processes: applications to computer code emulation and dynamical system recovery
- Hilbert space methods for reduced-rank Gaussian process regression
- Capturing ridge functions in high dimensions from point queries
- A near-stationary subspace for ridge approximation
Uses Software
This page was built for publication: Dimension reduction via Gaussian ridge functions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4960976)
