Papers
Topics
Authors
Recent
Search
2000 character limit reached

TransOpt: Transformer-based Representation Learning for Optimization Problem Classification

Published 29 Nov 2023 in cs.LG and math.OC | (2311.18035v1)

Abstract: We propose a representation of optimization problem instances using a transformer-based neural network architecture trained for the task of problem classification of the 24 problem classes from the Black-box Optimization Benchmarking (BBOB) benchmark. We show that transformer-based methods can be trained to recognize problem classes with accuracies in the range of 70\%-80\% for different problem dimensions, suggesting the possible application of transformer architectures in acquiring representations for black-box optimization problems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (11)
  1. U. Škvorc, T. Eftimov, and P. Korošec, “Understanding the problem space in single-objective numerical optimization using exploratory landscape analysis,” Applied Soft Computing, vol. 90, p. 106138, 2020. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1568494620300788
  2. G. Cenikj, R. Dieter Lang, A. Petrus Engelbrecht, C. Doerr, P. Korošec, and T. Eftimov, “SELECTOR: Selecting a Representative Benchmark Suite for Reproducible Statistical Comparison,” in Proceedings of The Genetic and Evolutionary Computation Conference, 2022, in Press.
  3. M. A. Muñoz and K. Smith-Miles, “Generating new space-filling test instances for continuous black-box optimization,” Evolutionary Computation, vol. 28, pp. 379–404, 09 2020.
  4. K. M. Malan and A. P. Engelbrecht, “A survey of techniques for characterising fitness landscapes and some possible ways forward,” Information Sciences, vol. 241, pp. 148–163, 2013. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0020025513003125
  5. O. Mersmann, B. Bischl, H. Trautmann, M. Preuss, C. Weihs, and G. Rudolph, “Exploratory landscape analysis,” in Proceedings of the 13th annual conference on Genetic and evolutionary computation, 2011, pp. 829–836.
  6. G. Petelin, G. Cenikj, and T. Eftimov, “Tla: Topological landscape analysis for single-objective continuous optimization problem instances,” in 2022 IEEE Symposium Series on Computational Intelligence (SSCI), 2022, pp. 1698–1705.
  7. M. V. Seiler, R. P. Prager, P. Kerschke, and H. Trautmann, “A collection of deep learning-based feature-free approaches for characterizing single-objective continuous fitness landscapes,” in Proceedings of the Genetic and Evolutionary Computation Conference, ser. GECCO ’22.   New York, NY, USA: Association for Computing Machinery, 2022, p. 657–665. [Online]. Available: https://doi.org/10.1145/3512290.3528834
  8. N. van Stein, F. X. Long, M. Frenzel, P. Krause, M. Gitterle, and T. Bäck, “Doe2vec: Deep-learning based features for exploratory landscape analysis,” 03 2023.
  9. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” 2017. [Online]. Available: https://arxiv.org/abs/1706.03762
  10. N. Hansen, S. Finck, R. Ros, and A. Auger, “Real-Parameter Black-Box Optimization Benchmarking 2009: Noiseless Functions Definitions,” INRIA, Research Report RR-6829, 2009. [Online]. Available: https://hal.inria.fr/inria-00362633
  11. N. Hansen, A. Auger, R. Ros, O. Mersmann, T. Tušar, and D. Brockhoff, “Coco: A platform for comparing continuous optimizers in a black-box setting,” Optimization Methods and Software, pp. 1–31, 2020.
Citations (5)

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.