Abstract
Multiobjective optimization problems with heterogeneous objectives are defined as those that possess significantly different types of objective function components (not just incommensurable in units or scale). For example, in a heterogeneous problem the objective function components may differ in formal computational complexity, practical evaluation effort (time, costs, or resources), determinism (stochastic vs deterministic), or some combination of all three. A particularly challenging variety of heterogeneity may occur by the combination of a time-consuming laboratory-based objective with other objectives that are evaluated using faster computer-based calculations. Perhaps more commonly, all objectives may be evaluated computationally, but some may require a lengthy simulation process while others are computed from a relatively simple closed-form calculation. In this chapter, we motivate the need for more work on the topic of heterogeneous objectives (with reference to real-world examples), expand on a basic taxonomy of heterogeneity types, and review the state of the art in tackling these problems. We give special attention to heterogeneity in evaluation time (latency) as this requires sophisticated approaches. We also present original experimental work on estimating the amount of heterogeneity in evaluation time expected in many-objective problems, given reasonable assumptions, and survey related research threads that could contribute to this area in future.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Solutions evaluated on the fast objective are considered for evaluation on the slow objective in the next generation if they outperform at least one of their parents on the fast objective.
References
P.D. Allison, Missing Data (Sage publications, 2001)
R.Ā Allmendinger, Tuning evolutionary search for closed-loop optimization. Ph.D. thesis, The University of Manchester, UK (2012)
R. Allmendinger, M.T.M. Emmerich, J. Hakanen, Y. Jin, E. Rigoni, Surrogate-assisted multicriteria optimization: complexities, prospective solutions, and business case. J. Multi-Criteria Decis. Anal. 24(1ā2), 5ā24 (2017)
R.Ā Allmendinger, S.Ā Gerontas, N.J. Titchener-Hooker, S.S. Farid, Tuning evolutionary multiobjective optimization for closed-loop estimation of chromatographic operating conditions, in Parallel Problem Solving from Nature (PPSN) (Springer, 2014), pp. 741ā750
R. Allmendinger, J. Handl, J.D. Knowles, Multiobjective optimization: when objectives exhibit non-uniform latencies. Eur. J. Oper. Res. 243(2), 497ā513 (2015)
R.Ā Allmendinger, J.D. Knowles, Evolutionary search in lethal environments, in International Conference on Evolutionary Computation Theory and Applications (SciTePress, 2011), pp. 63ā72
R.Ā Allmendinger, J.D. Knowles, āHang on a minuteā: investigations on the effects of delayed objective functions in multiobjective optimization, in Evolutionary Multi-criterion Optimization (EMO) (Springer, 2013), pp. 6ā20
R. Allmendinger, J.D. Knowles, On handling ephemeral resource constraints in evolutionary search. Evol. Comput. 21(3), 497ā531 (2013)
J.Ā Azimi, A.Ā Fern, X.Z. Fern, Batch bayesian optimization via simulation matching, in Neural Information Processing Systems (NIPS) (2010), pp. 109ā117
D. Bertsimas, M. Sim, M. Zhang, Adaptive distributionally robust optimization. Manag. Sci. 65(2), 604ā618 (2019)
D. Brockhoff, E. Zitzler, Objective reduction in evolutionary multiobjective optimization: Theory and applications. Evolutionary computation 17(2), 135ā166 (2009)
P. Brucker, A. Drexl, R. Mƶhring, K. Neumann, E. Pesch, Resource-constrained project scheduling: notation, classification, models, and methods. Eur. J. Oper. Res. 112(1), 3ā41 (1999)
L.Ā Cervante, B.Ā Xue, M.Ā Zhang, L.Ā Shang, Binary particle swarm optimisation for feature selection: a filter based approach, in Congress on Evolutionary Computation (CEC) (IEEE Press, 2012), pp. 1ā8
R. Cheng, Y. Jin, M. Olhofer, B. Sendhoff, A reference vector guided evolutionary algorithm for many-objective optimization. IEEE Trans. Evol. Comput. 20(5), 773ā791 (2016)
T.Ā Chugh, R.Ā Allmendinger, V.Ā Ojalehto, K.Ā Miettinen, Surrogate-assisted evolutionary biobjective optimization for objectives with non-uniform latencies, in Genetic and Evolutionary Computation Conference (GECCO) (ACM Press, 2018), pp. 609ā616
T. Chugh, Y. Jin, K. Miettinen, J. Hakanen, K. Sindhya, A surrogate-assisted reference vector guided evolutionary algorithm for computationally expensive many-objective optimization. IEEE Trans. Evol. Comput. 22(1), 129ā142 (2018)
G.Ā Eichfelder, X.Ā Gandibleux, M.J. Geiger, J.Ā Jahn, A.Ā Jaszkiewicz, J.D. Knowles, P.K. Shukla, H.Ā Trautmann, S.Ā Wessing, Heterogeneous functions (WG3), in Understanding Complexity in Multiobjective Optimization (Dagstuhl Seminar 15031) (Dagstuhl Zentrum fĆ¼r Informatik, 2015), pp. 121ā129
P.J. GarcĆa-Laencina, J.-L. Sancho-GĆ³mez, A.R. Figueiras-Vidal, Pattern classification with missing data: a review. Neural Comput. Appl. 19(2), 263ā282 (2010)
C. Gerth, P. Weidner, Nonconvex separation theorems and some applications in vector optimization. J. Optim. Theory Appl. 67(2), 297ā320 (1990)
D. Ginsbourger, J. Janusevskis, R. Le Riche, Dealing with asynchronicity in parallel Gaussian Process based global optimization Research report, Ecole de Mines Saint-Etienne, France (2011)
J.Ā GonzĆ”lez, Z.Ā Dai, P.Ā Hennig, N.D. Lawrence, Batch Bayesian Optimization via Local Penalization, in Artificial Intelligence and Statistics (AISTATS) (2016), pp. 648ā657. JMLR.org
S.Ā Greco, K.Ā Klamroth, J.D. Knowles, G.Ā Rudolph (eds.) Understanding Complexity in Multiobjective Optimization (Dagstuhl Seminar 15031), Dagstuhl Reports, vol. 5(1). Schloss DagstuhlāLeibniz-Zentrum fĆ¼r Informatik, Germany (2015)
T.Ā Jansen, C.Ā Zarges, Fixed budget computations: a different perspective on run time analysis, in Genetic and Evolutionary Computation Conference (GECCO) (ACM Press, 2012), pp. 1325ā1332
D.R. Jones, M. Schonlau, W.J. Welch, Efficient global optimization of expensive black-box functions. J. Global Optim. 13(4), 455ā492 (1998)
V.V. Kalashnikov, Mathematical Methods in Queuing Theory (Springer, 1994)
Y.Ā Kim, R.Ā Allmendinger, M.Ā LĆ³pez-IbƔƱez, Safe learning and optimization techniques: Towards a survey of the state of the art, in Trustworthy AI ā Integrating Learning, Optimization and Reasoning (TAILOR) (Springer, 2020), pp. 123ā139
J.D. Knowles, Closed-loop evolutionary multiobjective optimization. IEEE Comput. Intell. Mag. 4, 77ā91 (2009)
J.D. Knowles, D.Ā Corne, Instance generators and test suites for the multiobjective quadratic assignment problem, in Evolutionary Multi-criterion Optimization (EMO) (Springer, 2003), pp. 295ā310
A.Ā Lewis, S.Ā Mostaghim, I.Ā Scriven, Asynchronous multi-objective optimisation in unreliable distributed environments, in Biologically-Inspired Optimisation Methods (Springer, 2009), pp. 51ā78
R.J. Little, D.B. Rubin, Statistical Analysis with Missing Data (Wiley, 2019)
D.G. Malcolm, J.H. Roseboom, C.E. Clark, W. Fazar, Application of a technique for research and development program evaluation. Oper. Res. 7(5), 646ā669 (1959)
O.Ā Mersmann, B.Ā Bischl, H.Ā Trautmann, M.Ā Preuss, C.Ā Weihs, G.Ā Rudolph, Exploratory landscape analysis, in Genetic and Evolutionary Computation Conference (GECCO) (ACM Press, 2011), pp. 829ā836
S. OāHagan, W.B. Dunn, M. Brown, J.D. Knowles, D.B. Kell, Closed-loop, multiobjective optimization of analytical instrumentation: gas chromatography/time-of-flight mass spectrometry of the metabolomes of human serum and of yeast fermentations. Anal. Chem. 77(1), 290ā303 (2005)
S. OāHagan, W.B. Dunn, J.D. Knowles, D. Broadhurst, R. Williams, J.J. Ashworth, M. Cameron, D.B. Kell, Closed-loop, multiobjective optimization of two-dimensional gas chromatography/mass spectrometry for serum metabolomics. Anal. Chem. 79(2), 464ā476 (2007)
L.Ā Orseau, S.Ā Armstrong, Safely interruptible agents, in Conference on Uncertainty in Artificial Intelligence (AUAI Press, 2016), pp. 557ā566
S.J. Pan, Q. Yang, A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345ā1359 (2009)
L. Paquete, T. StĆ¼tzle, A study of stochastic local search algorithms for the biobjective QAP with correlated flow matrices. Eur. J. Oper. Res. 169(3), 943ā959 (2006)
M. Platt, W. Rowe, D.C. Wedge, D.B. Kell, J.D. Knowles, P.J.R. Day, Aptamer evolution for array-based diagnostics. Anal. Biochem. 390(2), 203ā205 (2009)
R.C. Purshouse, P.J. Fleming, On the evolutionary optimization of many conflicting objectives. IEEE Trans. Evolut. Comput. 11(6), 770ā784 (2007)
E.O. Scott, K.A. DeĀ Jong, Evaluation-time bias in asynchronous evolutionary algorithms, in Genetic and Evolutionary Computation Conference (GECCO) (ACM Press, 2015), pp. 1209ā1212
J.Ā Snoek, H.Ā Larochelle, R.P. Adams, Practical Bayesian optimization of machine learning algorithms, in Neural Information Processing Systems (NIPS) (2012), pp. 2951ā2959
M. Tabatabaei, J. Hakanen, M. Hartikainen, K. Miettinen, K. Sindhya, A survey on handling computationally expensive multiobjective optimization problems using surrogates: non-nature inspired methods. Struct. Multidiscip. Optim. 52(1), 1ā25 (2015)
E.-G. Talbi, S.Ā Mostaghim, T.Ā Okabe, H.Ā Ishibuchi, G.Ā Rudolph, C.A.C. Coello, Parallel approaches for multiobjective optimization, in Multiobjective Optimization (Springer, 2008), pp. 349ā372
J.Ā Thomann, A trust region approach for multi-objective heterogeneous optimization. Ph.D. thesis, Technische UniversitƤt Ilmenau, Germany, Ilmenau, Germany (2019)
J. Thomann, G. Eichfelder, Numerical results for the multiobjective trust region algorithm MHT. Data in Brief 25, 1ā18 (2019)
J. Thomann, G. Eichfelder, Representation of the Pareto front for heterogeneous multi-objective optimization. J. Appl. Numer. Optim 1(3), 293ā323 (2019)
J. Thomann, G. Eichfelder, A trust-region algorithm for heterogeneous multiobjective optimization. SIAM J. Optim. 29(2), 1017ā1047 (2019)
L. Van Der Maaten, E. Postma, J. Van den Herik, Dimensionality reduction: a comparative review. J. Mach. Learn Res. 10(66ā71), 13 (2009)
X. Wang, Y. Jin, S. Schmitt, M. Olhofer, An adaptive bayesian approach to surrogate-assisted evolutionary multi-objective optimization. Inf. Sci. 519, 317ā331 (2020)
X.Ā Wang, Y.Ā Jin, S.Ā Schmitt, M.Ā Olhofer, Transfer learning for Gaussian process assisted evolutionary bi-objective optimization for objectives with different evaluation times, in Genetic and Evolutionary Computation Conference (GECCO) (ACM Press, 2020), pp. 587ā594
M.Ā Yagoubi, L.Ā Thobois, M.Ā Schoenauer, Asynchronous evolutionary multi-objective algorithms with heterogeneous evaluation costs, in Congress of Evolutionary Computation (CEC) (IEEE Press, 2011), pp. 21ā28
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2023 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Allmendinger, R., Knowles, J. (2023). Heterogeneous Objectives: State-of-the-Art andĀ Future Research. In: Brockhoff, D., Emmerich, M., Naujoks, B., Purshouse, R. (eds) Many-Criteria Optimization and Decision Analysis. Natural Computing Series. Springer, Cham. https://doi.org/10.1007/978-3-031-25263-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-25263-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25262-4
Online ISBN: 978-3-031-25263-1
eBook Packages: Computer ScienceComputer Science (R0)