An Accelerated Sequential Algorithm for Producing<i>D</i>-Optimal Designs
SIAM Journal on Scientific and Statistical ComputingPublished 1 March 1989
Thomas G. Robertazzi, S.C. Schwartz
Citations41
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An extremely efficient algorithm is presented for generating D-optimal designs and it is shown that the underlying set function of the sequential design algorithm is submodular and thus the so-called accelerated greedy algorithm may be applied.
Abstract
An extremely efficient algorithm is presented for generating D-optimal designs. It is shown that the underlying set function of the sequential design algorithm is submodular and thus the so-called accelerated greedy algorithm may be applied to this problem. While the new algorithm’s statistical basis is identical to that of the Wynn and Federov algorithm, it requires significantly fewer function evaluations. The new algorithm is particularly useful when no prior information concerning the structure of the optimal design is available.
Keywords
Computer ScienceDecision SciencesEngineering
The Design and Analysis of Computer Algorithms
9,456 Citations1974Alfred V. Aho, John E. Hopcroft
This text introduces the basic data structures and programming techniques often used in efficient algorithms, and covers use of lists, push-down stacks, queues, trees, and graphs.
Proceedings of the American Mathematical SocietyOn the shortest spanning subtree of a graph and the traveling salesman problem
5,003 Citations1956Joseph B. Kruskal
Bell System Technical JournalComputer Solutions of the Traveling Salesman Problem
1,960 Citations1965Shen Lin
Two algorithms for solving the (symmetric distance) traveling salesman problem have been programmed for a high-speed digital computer and are based on a general heuristic approach believed to be of general applicability to various optimization problems.
Mathematical ProgrammingMatroids and the greedy algorithm
867 Citations1971Jack Edmonds
Linear-algebra rank is the solution to an especially tractable optimization problem which are linear programs relative to certain derived polyhedra.
The Annals of Mathematical StatisticsOptimum Designs in Regression Problems
792 Citations1959J. Kiefer, J. Wolfowitz
Mathematical programming studiesAn analysis of approximations for maximizing submodular set functions—II
558 Citations1978Marshall L. Fisher, G. L. Nemhauser +1 more
The Annals of Mathematical StatisticsThe Sequential Generation of $D$-Optimum Experimental Designs
472 Citations1970Henry P. Wynn
TechnometricsAn Algorithm for the Construction of "D-Optimal" Experimental Designs
426 Citations2000Toby J. Mitchell
Lecture notes in control and information sciencesAccelerated greedy algorithms for maximizing submodular set functions
425 Citations2005Michel Minoux
A family of approximate solution methods is studied : the greedy algorithms for optimal subset problems given a finite set E and a real valued function f on P(E) (the power set of E).
The Annals of Mathematical StatisticsOptimal Experimental Designs
323 Citations1966Samuel Karlin, W. J. Studden
TechnometricsD-Optimality for Regression Designs: A Review
279 Citations1975Ralph C. St. John, Norman R. Draper
TechnometricsD-Optimality for Regression Designs: A Review
254 Citations1975Rosalind M. John, N. R. Draper
The model and the design problem are stated and the way the criterion has been extended to non-linear models is reviewed, particularly those on the theory of design and algorithms for constructing D-optimum designs are discussed.
Lecture notes in control and information sciencesOptimal Experiment Design for Dynamic System Identification
178 Citations1979Arun Balakrishnan
A Tchebycheff system approach for continuous-time sampling rate design and a D-optimal designs are proposed for this type of system.
TechnometricsBranch-and-Bound Search for Experimental Designs Based on<i>D</i>Optimality and Other Criteria
141 Citations1982William J. Welch
Mathematics and Computers in SimulationOptimal experiment design for dynamic system identification
125 Citations1981
IEEE Transactions on Automatic ControlOptimization of measurement schedules and sensor designs for linear dynamic systems
122 Citations1976R.К. Mehra
TechnometricsTime- and Space-Saving Computer Methods, Related to Mitchell's DETMAX, for Finding D-Optimum Designs
115 Citations1980Zvi Galil, J. Kiefer
This work develops a family of computer search methods for finding optimum designs, that generalize and improve upon Mitchell's exchange and DETMAK algorithms, and has found a number of new optimum or improved designs using these methods.
IEEE Transactions on Automatic ControlOptimal nonuniform sampling interval and test-input design for identification of physiological systems from very limited data
67 Citations1979Francesco Mori, Joseph J. DiStefano
TechnometricsAspects of Optimal Design in Dynamic Systems
47 Citations1980D. M. Titterington
The application of optimal experimental design theory to models for dynamic systems is surveyed and applications are split roughly into those involving choice of input functions and those in which sampling rates also are selected.
Journal of the American Statistical AssociationOn the Sequential Construction of D-Optimal Designs
25 Citations1976Jia-Yeong Tsay
Annals of TelecommunicationsAlgorithmes gloutons et fonctions surmodulaires: Théorie et application à un problème de sécurité dans les réseaux de télécommunications
4 Citations1980Stéphane Biesel-Guitonneau
Lecture notes in control and information sciencesAn accelerated experimental design algorithm
1 Citations1982Thomas G. Robertazzi, S.C. Schwartz
It is shown that a sufficient condition for applying the accelerated greedy algorithm of M. Minoux to the design problem is satisfied, which allows the evaluation of quadratic forms to replace determinant evaluations.
Journal of Statistical Computation and SimulationOptimizing the measurement processing order for linear regression
1 Citations1988Thomas G. Robertazzi, S.C. Schwartz
The excellent performance of a locally optimal greedy strategy which produces non–infereior (Pareto) orderings in the context of multi–criterion optimization is evaluated from the viewpoint of optimal replicated experimental design theory.