• Corpus ID: 196831739

Embedded Ridge Approximations: Constructing Ridge Approximations Over Localized Scalar Fields For Improved Simulation-Centric Dimension Reduction

  title={Embedded Ridge Approximations: Constructing Ridge Approximations Over Localized Scalar Fields For Improved Simulation-Centric Dimension Reduction},
  author={Chun Yui Wong and Pranay Seshadri and Geoffrey T. Parks and Mark A. Girolami},
Many quantities of interest (qois) arising from differential-equation-centric models can be resolved into functions of scalar fields. Examples of such qois include the lift over an airfoil or the displacement of a loaded structure; examples of corresponding fields are the static pressure field in a computational fluid dynamics solution, and the strain field in the finite element elasticity analysis. These scalar fields are evaluated at each node within a discretized computational domain. In… 

Optimization by moving ridge functions: derivative-free optimization for computationally intensive functions

A novel derivative-free algorithm, called optimization by moving ridge functions (OMoRF), for unconstrained and bound-constrained optimization is presented. This algorithm couples trust region

A Lanczos-Stieltjes method for one-dimensional ridge function approximation and integration

The key elements of the method are approximating the univariate density of the given linear combination of inputs by repeated convolutions and a Lanczos-Stieltjes method for constructing orthogonal polynomials and Gaussian quadrature.

Erratum: Active Subspace Methods in Theory and Practice: Applications to Kriging Surfaces

This work presents a method to first detect the directions of the strongest variability using evaluations of the gradient and subsequently exploit these directions to construct a response surface on a low-dimensional subspace---i.e., the active subspace ---of the inputs.

Data-Driven Polynomial Ridge Approximation Using Variable Projection

The Gauss-Newton method has superior theoretical guarantees and faster convergence than the alternating approach for polynomial ridge approximation earlier proposed by Constantine, Eftekhari, Hokanson, and Ward.

Dimension Reduction via Gaussian Ridge Functions

This paper develops an iterative algorithm that optimizes over the Grassmann manifold to compute the subspace, followed by an optimization of the hyperparameters of the Gaussian process to approximate a Gaussian ridge function.

Multifidelity Dimension Reduction via Active Subspaces

This work provides a non-asymptotic analysis of the number of gradient evaluations sufficient to achieve a prescribed error in the active subspace matrix, both in expectation and with high probability.

Uncertainty quantification of the transonic flow around the RAE 2822 airfoil

Motivated by the RAE 2822 test case, a Simplex Elements Stochastic Collocation (SESC) method is developed that combines a robust approximation of discon-tinuous responses with an efficient discretization in multi–dimensional probability spaces.

Inverse regression for ridge recovery: a data-driven approach for parameter reduction in computer experiments

This work interprets SDR methods sliced inverse regression (SIR) and sliced average variance estimation (SAVE) as estimating the directions of a ridge function, which is a composition of a low-dimensional linear transformation with a nonlinear function.

Computing active subspaces efficiently with gradient sketching

This work numerically study two methods for estimating the necessary eigenpairs of a matrix derived from the function's gradient using only linear measurements of the function’s gradient.

Gradient-Based Dimension Reduction of Multivariate Vector-Valued Functions

A gradient-based method for detecting and exploiting low-dimensional input parameter dependence of multivariate functions and reveals that the choice of norm on the codomain of the function can have a significant impact on the function's low- dimensional approximation.

Leakage Uncertainties in Compressors: The Case of Rotor 37

This paper revisits an old problem of validating computational fluid dynamics simulations with experiments in turbomachinery. The case considered here is NASA rotor 37. Prior computational fluid