Journal article · 2026 · Open access
Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning
SIAM Review, 68(3), 656–683 · Published 6 August 2026 · DOI 10.1137/24m1658875
In brief
“Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning” is a 2026 journal article by Junaid Akhter and 4 co-authors, published in SIAM Review. OpenAlex counts 3 citations as of 17 November 2026, which puts it in the top 9% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 3
- Most cited in
- 2025 (2)
- Field-weighted impact
- 2.37
- References
- 96
- Authors
- 5
Abstract
Recently, there has been increasing interest in the application of multiobjective optimization (MOO) in machine learning (ML). This interest is driven by the numerous real-life situations in which multiple objectives must be optimized simultaneously. A key aspect of MOO is the existence of a Pareto set, rather than a single optimal solution, which represents the optimal trade-offs between different objectives. Despite its potential, there is a noticeable lack of satisfactory literature serving as an entry-level guide for ML practitioners aiming to apply MOO effectively. In this paper, our goal is to provide such a resource and highlight pitfalls to avoid. We begin by establishing the groundwork for MOO, focusing on well-known approaches such as the weighted sum (WS) method alongside more advanced techniques like the multiobjective gradient descent algorithm (MGDA). We critically review existing studies across various ML fields in which MOO has been applied and identify challenges that can lead to incorrect interpretations. One of these fields is physics informed neural networks (PINNs), which we use as a guiding example to carefully construct experiments illustrating these pitfalls. By comparing WS and MGDA with one of the most common evolutionary algorithms, NSGA-II, we demonstrate that difficulties can arise regardless of the specific MOO method used. We emphasize the importance of understanding the specific problem, the objective space, and the selected MOO method, while also noting that the neglect of factors such as convergence criteria can result in misleading experiments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Akhter, J., Fährmann, P. D., Sonntag, K., Peitz, S., & Schwietert, D. (2026). Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning. SIAM Review, 68(3), 656–683. https://doi.org/10.1137/24m1658875
MLA 9
Akhter, Junaid, et al. “Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning.” SIAM Review, vol. 68, no. 3, 2026, pp. 656–683. https://doi.org/10.1137/24m1658875.
Chicago
Akhter, Junaid, Paul David Fährmann, Konstantin Sonntag, Sebastian Peitz, and Daniel Schwietert. 2026. “Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning.” SIAM Review 68 (3): 656–683. https://doi.org/10.1137/24m1658875.
Harvard
Akhter, J. et al. (2026) ‘Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning’, SIAM Review, 68(3), pp. 656–683. doi:10.1137/24m1658875.
IEEE
J. Akhter, P. D. Fährmann, K. Sonntag, S. Peitz, and D. Schwietert, “Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning,” SIAM Review, vol. 68, no. 3, pp. 656–683, 2026, doi: 10.1137/24m1658875.
BibTeX
@article{akhter2026common,
title = {{Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning}},
author = {Akhter, Junaid and Fährmann, Paul David and Sonntag, Konstantin and Peitz, Sebastian and Schwietert, Daniel},
journal = {SIAM Review},
year = {2026},
volume = {68},
number = {3},
pages = {656--683},
doi = {10.1137/24m1658875},
url = {https://doi.org/10.1137/24m1658875}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computational Theory and Mathematics › Advanced Multi-Objective Optimization Algorithms
- multi-objective optimization
- machine learning
- Pareto set
- simple additive weighting
- physics-informed neural networks
- NSGA-II
- evolutionary algorithms
- convergence conditions
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Akhter, J., Fährmann, P. D., Sonntag, K., Peitz, S., & Schwietert, D. (2026). Common Pitfalls to Avoid While Using Multiobjective Optimization in Machine Learning. SIAM Review, 68(3), 656–683. https://doi.org/10.1137/24m1658875
How many times has this paper been cited?
3 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Junaid Akhter, Paul David Fährmann, Konstantin Sonntag, Sebastian Peitz, Daniel Schwietert.
What is the DOI of this paper?
10.1137/24m1658875, permanently at https://doi.org/10.1137/24m1658875. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.