Evolutionary Hyperparameter Optimization

Evolutionary Hyperparameter Optimization is an optimization method that employs evolutionary algorithms to automatically discover optimal hyperparameter configurations for machine learning models by iteratively evolving a population of candidate solutions based on fitness evaluation and genetic operations.

117

Publications

6.8K

Citations

406

Authors

192

Institutions

Publications per year

2017–2026

88

Authors

406

  1. HW
    Harvey Wu

    Columbia University, United States

    2 publications · 104 citations

    2

    h-index

  2. SR
    Steven R. Young

    Oak Ridge National Laboratory, United States

    2 publications · 473 citations

    2

    h-index

  3. RM
    Risto Miikkulainen

    The University of Texas at Austin, United States

    2 publications · 121 citations

    2

    h-index

  4. TP
    Thomas P. Karnowski

    Oak Ridge National Laboratory, United States

    2 publications · 473 citations

    2

    h-index

  5. JL
    Jason Liang

    The University of Texas at Austin, United States

    2 publications · 121 citations

    2

    h-index

1–5 of 406

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 271 citations

    9

    h-index

  2. IEEE Access

    4 publications · 195 citations

    4

    h-index

  3. Expert Systems with Applications

    4 publications · 351 citations

    4

    h-index

  4. Neurocomputing

    3 publications · 649 citations

    3

    h-index

  5. Soft Computing

    3 publications · 109 citations

    3

    h-index

1–5