Minimax optimal designs via particle swarm optimization methods
read more
Citations
A Modified Particle Swarm Optimization Technique for Finding Optimal Designs for Mixture Models
Algorithmic Searches for Optimal Designs
Optimal robust control strategy of a solid oxide fuel cell system
Cluster-Randomized Trial to Increase Hepatitis B Testing among Koreans in Los Angeles.
Using animal instincts to design efficient biomedical studies via particle swarm optimization
References
Particle swarm optimization
A new optimizer using particle swarm theory
A modified particle swarm optimizer
Parameter Selection in Particle Swarm Optimization
Comparing inertia weights and constriction factors in particle swarm optimization
Related Papers (5)
Frequently Asked Questions (7)
Q2. What have the authors stated for future works in "Minimax optimal designs via particle swarm optimization methods" ?
The authors have two areas for future work. The second area for future work is to apply PSO to find optimal designs under a non-convex criterion, where the authors no longer have an equivalence theorem to confirm whether a design is optimal or not. The authors plan to apply PSO methodology to find these types of optimal designs and hope to report results in the near future. The authors thank the editorial team for all the helpful comments and suggestions.
Q3. What are the key tuning parameters in the PSOmethod?
The key tuning parameters in the PSOmethod are (i) flock size, i.e. number of particles (designs) to use in the search, (ii) the number of common support points these designs have, and (iii) the number of iterations allowed in the search process.
Q4. What is the weights used in the optimal design?
The weightstypically used in popular algorithms such as Fedorov’s algorithm for finding optimal designs to combine designs from each successive iterations are between 0 and 1 and have the following properties: (a) their sum is infinity and (b) the sum of squares of each term is finite.
Q5. How did the PSO algorithm find the minimax optimal design for Example 2?
The numerically minimax optimal design for Example 2 was found by repeated guess work followed by confirmation with the equivalence theorem in King and Wong (2000) with the aid of Mathematica.
Q6. What is the way to solve a minimax problem?
Optimal minimax designs for nonlinear models can be challenging even when there are just two parameters in the model; earlier attempts to solve such minimax problems have to impose constraints to simplify the optimization problem.
Q7. What is the way to find the minimax optimal design for the quadratic model?
the authors applied Nested PSO and tested if it can find the minimax optimal design for the quadratic model with a monotonic increasing efficiency function when (a) X = Z and (b) Z is outside of X .