Computing optimal designs of multiresponse experiments reduces to second-order cone program\-ming
From MaRDI portal
Publication:629098
DOI10.1016/J.JSPI.2010.11.031zbMATH Open1207.62156arXiv0912.5467OpenAlexW2962760613MaRDI QIDQ629098FDOQ629098
Authors: Guillaume Sagnol 
Publication date: 8 March 2011
Published in: Journal of Statistical Planning and Inference (Search for Journal in Brave)
Abstract: Elfving's Theorem is a major result in the theory of optimal experimental design, which gives a geometrical characterization of optimality. In this paper, we extend this theorem to the case of multiresponse experiments, and we show that when the number of experiments is finite, and optimal design of multiresponse experiments can be computed by Second-Order Cone Programming (SOCP). Moreover, our SOCP approach can deal with design problems in which the variable is subject to several linear constraints. We give two proofs of this generalization of Elfving's theorem. One is based on Lagrangian dualization techniques and relies on the fact that the semidefinite programming (SDP) formulation of the multiresponse optimal design always has a solution which is a matrix of rank . Therefore, the complexity of this problem fades. We also investigate a emph{model robust} generalization of optimality, for which an Elfving-type theorem was established by Dette (1993). We show with the same Lagrangian approach that these model robust designs can be computed efficiently by minimizing a geometric mean under some norm constraints. Moreover, we show that the optimality conditions of this geometric programming problem yield an extension of Dette's theorem to the case of multiresponse experiments. When the number of unknown parameters is small, or when the number of linear functions of the parameters to be estimated is small, we show by numerical examples that our approach can be between 10 and 1000 times faster than the classic, state-of-the-art algorithms.
Full work available at URL: https://arxiv.org/abs/0912.5467
Recommendations
- Computing exact \(D\)-optimal designs by mixed integer second-order cone programming
- Optimal design of multi-response experiments using semi-definite programming
- Optimal design of experiments via linear programming
- Approximate and exact optimal designs for \(2^k\) factorial experiments for generalized linear models via second order cone programming
- Computing \(c\)-optimal experimental designs using the simplex method of linear programming
Cites Work
- Using SeDuMi 1.02, A Matlab toolbox for optimization over symmetric cones
- Title not available (Why is that?)
- On linear regression designs which maximize information
- Elfving's theorem revisited
- Title not available (Why is that?)
- Optimum Allocation in Linear Regression Theory
- Elfving's theorem for \(D\)-optimality
- Computing \(c\)-optimal experimental designs using the simplex method of linear programming
- General equivalence theory for optimum designs (approximate theory)
- Title not available (Why is that?)
- Improvements on removing nonoptimal support points in \(D\)-optimum design algorithms
- Improving updating rules in multiplicative algorithms for computing \(D\)-optimal designs
- Monotonic convergence of a general algorithm for computing optimal designs
- The Sequential Generation of $D$-Optimum Experimental Designs
- Applications of second-order cone programming
- Experimental design in a class of models
- A geometric characterization of \(c\)-optimal designs for heteroscedastic regression
- Potential Reduction Polynomial Time Method for Truss Topology Design
- Determinant Maximization with Linear Matrix Inequality Constraints
- Invited Discussion Paper Constrained Optimization of Experimental Design
- Elfving's Theorem and Optimal Designs for Quadratic Loss
- Geometry of \(E\)-optimality
- Removing non-optimal support points in \(D\)-optimum design algorithms.
- A class of semidefinite programs with rank-one solutions
- Gustav Elfving's impact on experimental design.
- Minimax designs in linear regression models
- One hundred years of the design of experiments on and off the pages of Biometrika
- Submodularity and randomized rounding techniques for optimal experimental design
- Randomized Algorithms for Semi-Infinite Programming Problems
Cited In (37)
- A class of semidefinite programs with rank-one solutions
- Multiplicative methods for computing \(D\)-optimal stratified designs of experiments
- Optimal design for prediction in multiresponse linear models based on rectangular confidence region
- Generation of point sets by convex optimization for interpolation in reproducing kernel Hilbert spaces
- T-optimal designs for multi-factor polynomial regression models via a semidefinite relaxation method
- Removing inessential points in \(c\)-and \(A\)-optimal design
- Optimal Designs for Multi-Response Nonlinear Regression Models With Several Factors via Semidefinite Programming
- Design of c-optimal experiments for high-dimensional linear models
- On the semidefinite representation of real functions applied to symmetric matrices
- A semidefinite programming study of the Elfving theorem
- Computing efficient exact designs of experiments using integer quadratic programming
- Computing exact \(D\)-optimal designs by mixed integer second-order cone programming
- Computing optimal experimental designs via interior point method
- Equivalence of weighted and partial optimality of experimental designs
- Adaptive grid semidefinite programming for finding optimal designs
- Construction of constrained experimental designs on finite spaces for a modified \(\mathrm{E}_k\)-optimality criterion
- An algorithm based on semidefinite programming for finding minimax optimal designs
- Finding Bayesian Optimal Designs for Nonlinear Models: A Semidefinite Programming‐Based Approach
- ForLion: a new algorithm for D-optimal designs under general parametric statistical models with mixed factors
- Quasi-Newton algorithm for optimal approximate linear regression design: optimization in matrix space
- Approximate and exact optimal designs for \(2^k\) factorial experiments for generalized linear models via second order cone programming
- An unexpected connection between Bayes \(A\)-optimal designs and the group Lasso
- Mixed-integer linear programming for computing optimal experimental designs
- A Randomized Exchange Algorithm for Computing Optimal Approximate Designs of Experiments
- Network-related problems in optimal experimental design and second order cone programming
- Least squares polynomial chaos expansion: a review of sampling strategies
- Evaluation of Combinatorial Optimisation Algorithms for c-Optimal Experimental Designs with Correlated Observations
- Optimal experimental design for linear time invariant state-space models
- Optimal design of multifactor experiments via grid exploration
- Optimal design of multi-response experiments using semi-definite programming
- Optimal dose‐finding for efficacy–safety models
- Computing \(c\)-optimal experimental designs using the simplex method of linear programming
- Optimal exact designs of experiments via mixed integer nonlinear programming
- A semi-infinite programming based algorithm for finding minimax optimal designs for nonlinear models
- Exact optimal experimental designs with constraints
- Barycentric algorithm for computing D-optimal size- and cost-constrained designs of experiments
- Optimal Design of Experiments for Implicit Models
Uses Software
This page was built for publication: Computing optimal designs of multiresponse experiments reduces to second-order cone program\-ming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q629098)
