Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Wang, Handing; Jin, Yaochu; Jansen, Jan O.

doi:10.1109/tevc.2016.2555315

Cited by 189 publications

(102 citation statements)

References 71 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…Peitz et al [107] POD-based multiobjective optimal control of the NavierStokes equations via scalarization and set-oriented methods Wang et al [122] MOEA with multifidelity surrogate-management and offline-online decomposition applied to a Trauma system…”

Section: Applicationsmentioning

confidence: 99%

A Survey of Recent Trends in Multiobjective Optimal Control -- Surrogate Models, Feedback Control and Objective Reduction

Peitz¹,

Dellnitz²

2018

Preprint

View full text Add to dashboard Cite

Abstract:Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to compute the set of optimal compromises (the Pareto set) between the conflicting objectives. The advances in algorithms and the increasing interest in Pareto optimal solutions have led to a wide range of new applications related to optimal and feedback control which results in new challenges such as expensive models or real-time applicability. Since the Pareto set generally consists of an infinite number of solutions, the computational effort can quickly become challenging which is particularly problematic when the objectives are costly to evaluate or when a solution has to be presented very quickly. This article gives an overview over recent developments in accelerating multiobjective optimal control for complex problems where either PDE constraints are present or where a feedback behavior has to be achieved. In the first case, surrogate models yield significant speed-ups. Besides classical meta-modeling techniques for multiobjective optimization, a promising alternative for control problems is to introduce a surrogate model for the system dynamics. In the case of real-time requirements, various promising model predictive control approaches have been proposed, using either fast online solvers or offline-online decomposition. We also briefly comment on dimension reduction in many-objective optimization problems as another technique for reducing the numerical effort.

show abstract

Section: Applicationsmentioning

confidence: 99%

A Survey of Recent Trends in Multiobjective Optimal Control -- Surrogate Models, Feedback Control and Objective Reduction

Peitz¹,

Dellnitz²

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Commonly used models such as Gaussian processes (also known as Kriging) or support vector machines [11,22] are based on the similarity of candidate solutions. Similarity-based surrogate models have been used in such varied domains as: shape optimization in fluid dynamics [3,19], the discovery of new drugs [5], the placement of hospital trauma centers [29], and even to the optimization of other machine learning methods [23,27]. To produce a prediction these models interpolate based on the distance of a candidate solution to known examples.…”

Section: Introductionmentioning

confidence: 99%

Prediction of neural network performance by phenotypic modeling

Hagg

Zaefferer

Stork

et al. 2019

Proceedings of the Genetic and Evolutionary Computation Conference Companion

View full text Add to dashboard Cite

Surrogate models are used to reduce the burden of expensive-toevaluate objective functions in optimization. By creating models which map genomes to objective values, these models can estimate the performance of unknown inputs, and so be used in place of expensive objective functions. Evolutionary techniques such as genetic programming or neuroevolution commonly alter the structure of the genome itself. A lack of consistency in the genotype is a fatal blow to data-driven modeling techniques: interpolation between points is impossible without a common input space. However, while the dimensionality of genotypes may differ across individuals, in many domains, such as controllers or classifiers, the dimensionality of the input and output remains constant. In this work we leverage this insight to embed differing neural networks into the same input space. To judge the difference between the behavior of two neural networks, we give them both the same input sequence, and examine the difference in output. This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology. In a robotic navigation task, we show that models trained using this phenotypic embedding perform as well or better as those trained on the weight values of a fixed topology neural network. We establish such phenotypic surrogate models as a promising and flexible approach which enables surrogate modeling even for representations that undergo structural changes.

show abstract

“…Over the past decades, many efficient SAEAs has been proposed and applied into complex real-world applications, such as trauma system [23]. Individual-based model control [10] method is the most effective strategy that a few individuals will be re-evaluated by the actual function in each generation according to different criteria.…”

Section: Introductionmentioning

confidence: 99%

Algorithm portfolio for individual-based surrogate-assisted evolutionary algorithms

Hao

Liu

Yao

2019

Proceedings of the Genetic and Evolutionary Computation Conference

View full text Add to dashboard Cite

Surrogate-assisted evolutionary algorithms (SAEAs) are powerful optimisation tools for computationally expensive problems (CEPs). However, a randomly selected algorithm may fail in solving unknown problems due to no free lunch theorems, and it will cause more computational resource if we re-run the algorithm or try other algorithms to get a much solution, which is more serious in CEPs. In this paper, we consider an algorithm portfolio for SAEAs to reduce the risk of choosing an inappropriate algorithm for CEPs. We propose two portfolio frameworks for very expensive problems in which the maximal number of fitness evaluations is only 5 times of the problem's dimension. One framework named Par-IBSAEA runs all algorithm candidates in parallel and a more sophisticated framework named UCB-IBSAEA employs the Upper Confidence Bound (UCB) policy from reinforcement learning to help select the most appropriate algorithm at each iteration. An effective reward definition is proposed for the UCB policy. We consider three state-of-the-art individual-based SAEAs on different problems and compare them to the portfolios built from their instances on several benchmark problems given limited computation budgets. Our experimental studies demonstrate that our proposed portfolio frameworks significantly outperform any single algorithm on the set of benchmark problems.

show abstract

Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System

Cited by 189 publications

References 71 publications

A Survey of Recent Trends in Multiobjective Optimal Control -- Surrogate Models, Feedback Control and Objective Reduction

A Survey of Recent Trends in Multiobjective Optimal Control -- Surrogate Models, Feedback Control and Objective Reduction

Prediction of neural network performance by phenotypic modeling

Algorithm portfolio for individual-based surrogate-assisted evolutionary algorithms

Contact Info

Product

Resources

About