Seeding the initial population of multi-objective evolutionary algorithms: A computational study

@article{Friedrich2015SeedingTI,
  title={Seeding the initial population of multi-objective evolutionary algorithms: A computational study},
  author={Tobias Friedrich and Markus Wagner},
  journal={Appl. Soft Comput.},
  year={2015},
  volume={33},
  pages={223-230}
}
Graphical abstractDisplay Omitted HighlightsWe study the benefits of seeding for multi-objective optimization algorithms.We investigate two approaches for five state-of-the-art algorithms on 48 functions.Different optimization algorithms benefit very differently from seeding.AGE and SMS-EMOA typically achieve the best approximation of the true Pareto front. Most experimental studies initialize the population of evolutionary algorithms with random genotypes. In practice, however, optimizers are… 
Seeding the initial population with feasible solutions in metaheuristic optimization of steel trusses
In spite of considerable research work on the development of efficient algorithms for discrete sizing optimization of steel truss structures, only a few studies have addressed non-algorithmic issues
Seeding the initial population with feasible solutions in metaheuristic optimization of steel trusses
In spite of considerable research work on the development of efficient algorithms for discrete sizing optimization of steel truss structures, only a few studies have addressed non-algorithmic issues
Responsive Multi-population Models for the Dynamic Travelling Thief Problem
TLDR
A multi-population model is proposed to improve optimisation performance on the recent dynamic formulations of the Travelling Thief Problem and a key feature of this model relates to how the currency of exploitable problem information can be used for population seeding in response to dynamic events.
Dynamic Multi-objective Optimization of the Travelling Thief Problem
TLDR
A combined approach that mixes solution generation methods to provide a composite population in response to dynamic changes provides improved performance in some instances for the different dynamic TTP formulations.
Multi-Objective Ant Colony Optimization Based on the Physarum-Inspired Mathematical Model for Bi-Objective Traveling Salesman Problems
TLDR
The optimized algorithms, named as iPM-MOACOs, can enhance the pheromone in the short paths and promote the search ability of ants and achieve a better compromise solution than the original MOACOs for solving bTSPs.
Scheduling multi-objective unrelated parallel machines using hybrid reference-point based NSGA-II algorithm
This paper addresses the multi-objective unrelated parallel machines to minimize makespan, total weighted completion times, and total weighted tardiness simultaneously. To tackle this problem, a
Incorporating expert knowledge into evolutionary algorithms with operators and constraints to design satellite systems
Abstract Knowledge-intensive evolutionary algorithms (EA) and knowledge-driven optimization algorithms that leverage problem- or domain-specific knowledge have been shown to discover high-quality
An improved partheno-genetic algorithm for the multi-constrained problem of curling match arrangement
TLDR
Simulation results demonstrate that the improved algorithm can solve the curling-match multi-constrained optimization problem efficiently and an eliminate-selection strategy is proposed to increase population diversity.
Fast Optimal Network Reconfiguration With Guided Initialization Based on a Simplified Network Approach
TLDR
The results show the ability of the proposed method to obtain the optimal solution within fast computational time and with superior consistency compared to the conventional methods.
Constraints in multi-objective optimization of land use allocation - Repair or penalize?
TLDR
This study shows that using repair mechanisms seems to be more effective in exploring the feasible solution space while penalizing constraint violation likely results in infeasible solutions.
...
1
2
3
...

References

SHOWING 1-10 OF 51 REFERENCES
Efficient parent selection for Approximation-Guided Evolutionary multi-objective optimization
TLDR
This work investigates different algorithm-specific selection strategies for AGE and presents several improved selections schemes that are computationally efficient and substantially improve AGE on low-dimensional objective spaces, but have no negative effect in high- dimensional objective spaces.
Seeding the initial population of a multi-objective evolutionary algorithm using gradient-based information
TLDR
This work adopts a steepest descent method to generate some nondominated points which are then used to seed the initial population of a multi-objective evolutionary algorithm (MOEA), which will spread them along the Pareto front.
Efficient optimization of many objectives by approximation-guided evolution
TLDR
This paper presents a framework for evolutionary multi-objective optimization that allows to work with a formal notion of approximation, and compares AGE with two additional algorithms that use very fast hypervolume-approximations to guide their search.
Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach
TLDR
The proof-of-principle results obtained on two artificial problems as well as a larger problem, the synthesis of a digital hardware-software multiprocessor system, suggest that SPEA can be very effective in sampling from along the entire Pareto-optimal front and distributing the generated solutions over the tradeoff surface.
Effects of population initialization on differential evolution for large scale optimization
TLDR
The optimal parameter configurations which can lead to the statistically superior performance over the CEC-2013 large-scale test problems are revealed and interestingly favour much larger population sizes while agreeing with the other parameter settings compared to the most commonly employed parameter configuration.
Comparison of Multiobjective Evolutionary Algorithms: Empirical Results
TLDR
This paper provides a systematic comparison of various evolutionary approaches to multiobjective optimization using six carefully chosen test functions and shows that elitism is shown to be an important factor for improving evolutionary multiobjectives search.
A fast approximation-guided evolutionary multi-objective algorithm
TLDR
The experiments show that AGE-II performs very well for multi-objective problems having few as well as many objectives, and it scales well with the number of objectives and enables practitioners to add objectives to their problems at small additional computational cost.
Scalable Test Problems for Evolutionary Multiobjective Optimization
TLDR
Three different approaches for systematically designing test problems for systematically demonstrating the efficacy of multiobjective evolutionary algorithms in handling problems having more than two objectives are suggested.
Dynamic multi-objective optimization with evolutionary algorithms: a forward-looking approach
TLDR
Initial results indicate that the approach improves algorithm performance, especially in problems where the frequency of objective change is high, and creates a robust algorithm for dynamic optimization.
An EMO Algorithm Using the Hypervolume Measure as Selection Criterion
TLDR
A steady-state EMOA will be devised, that combines concepts of non-dominated sorting with a selection operator based on the hypervolume measure, and achieves good convergence to the Pareto front and outperforms standard methods in the hyper volume covered.
...
1
2
3
4
5
...