---
_id: '46307'
abstract:
- lang: eng
  text: Exploratory Landscape Analysis is a powerful technique for numerically characterizing
    landscapes of single-objective continuous optimization problems. Landscape insights
    are crucial both for problem understanding as well as for assessing benchmark
    set diversity and composition. Despite the irrefutable usefulness of these features,
    they suffer from their own ailments and downsides. Hence, in this work we provide
    a collection of different approaches to characterize optimization landscapes.
    Similar to conventional landscape features, we require a small initial sample.
    However, instead of computing features based on that sample, we develop alternative
    representations of the original sample. These range from point clouds to 2D images
    and, therefore, are entirely feature-free. We demonstrate and validate our devised
    methods on the BBOB testbed and predict, with the help of Deep Learning, the high-level,
    expert-based landscape properties such as the degree of multimodality and the
    existence of funnel structures. The quality of our approaches is on par with methods
    relying on the traditional landscape features. Thereby, we provide an exciting
    new perspective on every research area which utilizes problem information such
    as problem understanding and algorithm design as well as automated algorithm configuration
    and selection.
author:
- first_name: Moritz
  full_name: Seiler, Moritz
  id: '105520'
  last_name: Seiler
- first_name: Raphael Patrick
  full_name: Prager, Raphael Patrick
  last_name: Prager
- first_name: Pascal
  full_name: Kerschke, Pascal
  last_name: Kerschke
- first_name: Heike
  full_name: Trautmann, Heike
  id: '100740'
  last_name: Trautmann
  orcid: 0000-0002-9788-8282
citation:
  ama: 'Seiler M, Prager RP, Kerschke P, Trautmann H. A Collection of Deep Learning-based
    Feature-Free Approaches for Characterizing Single-Objective Continuous Fitness
    Landscapes. In: <i>Proceedings of the Genetic and Evolutionary Computation Conference</i>.
    Association for Computing Machinery; 2022:657–665. doi:<a href="https://doi.org/10.1145/3512290.3528834">10.1145/3512290.3528834</a>'
  apa: Seiler, M., Prager, R. P., Kerschke, P., &#38; Trautmann, H. (2022). A Collection
    of Deep Learning-based Feature-Free Approaches for Characterizing Single-Objective
    Continuous Fitness Landscapes. <i>Proceedings of the Genetic and Evolutionary
    Computation Conference</i>, 657–665. <a href="https://doi.org/10.1145/3512290.3528834">https://doi.org/10.1145/3512290.3528834</a>
  bibtex: '@inproceedings{Seiler_Prager_Kerschke_Trautmann_2022, place={New York,
    NY, USA}, title={A Collection of Deep Learning-based Feature-Free Approaches for
    Characterizing Single-Objective Continuous Fitness Landscapes}, DOI={<a href="https://doi.org/10.1145/3512290.3528834">10.1145/3512290.3528834</a>},
    booktitle={Proceedings of the Genetic and Evolutionary Computation Conference},
    publisher={Association for Computing Machinery}, author={Seiler, Moritz and Prager,
    Raphael Patrick and Kerschke, Pascal and Trautmann, Heike}, year={2022}, pages={657–665}
    }'
  chicago: 'Seiler, Moritz, Raphael Patrick Prager, Pascal Kerschke, and Heike Trautmann.
    “A Collection of Deep Learning-Based Feature-Free Approaches for Characterizing
    Single-Objective Continuous Fitness Landscapes.” In <i>Proceedings of the Genetic
    and Evolutionary Computation Conference</i>, 657–665. New York, NY, USA: Association
    for Computing Machinery, 2022. <a href="https://doi.org/10.1145/3512290.3528834">https://doi.org/10.1145/3512290.3528834</a>.'
  ieee: 'M. 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 <i>Proceedings of the Genetic and Evolutionary
    Computation Conference</i>, 2022, pp. 657–665, doi: <a href="https://doi.org/10.1145/3512290.3528834">10.1145/3512290.3528834</a>.'
  mla: Seiler, Moritz, et al. “A Collection of Deep Learning-Based Feature-Free Approaches
    for Characterizing Single-Objective Continuous Fitness Landscapes.” <i>Proceedings
    of the Genetic and Evolutionary Computation Conference</i>, Association for Computing
    Machinery, 2022, pp. 657–665, doi:<a href="https://doi.org/10.1145/3512290.3528834">10.1145/3512290.3528834</a>.
  short: 'M. Seiler, R.P. Prager, P. Kerschke, H. Trautmann, in: Proceedings of the
    Genetic and Evolutionary Computation Conference, Association for Computing Machinery,
    New York, NY, USA, 2022, pp. 657–665.'
date_created: 2023-08-04T07:15:59Z
date_updated: 2024-06-07T07:13:23Z
department:
- _id: '34'
- _id: '819'
doi: 10.1145/3512290.3528834
language:
- iso: eng
page: 657–665
place: New York, NY, USA
publication: Proceedings of the Genetic and Evolutionary Computation Conference
publication_identifier:
  isbn:
  - '9781450392372'
publisher: Association for Computing Machinery
status: public
title: A Collection of Deep Learning-based Feature-Free Approaches for Characterizing
  Single-Objective Continuous Fitness Landscapes
type: conference
user_id: '15504'
year: '2022'
...