Model Complexity

Model Complexity is a theoretical construct in statistical learning that characterizes the flexibility of a model in approximating the underlying data-generating function, distinguished by its capacity to fit varying levels of noise and signal in the training data.

2.5K

Publications

204.6K

Citations

7.2K

Authors

2.1K

Institutions

Publications per year

2017–2026

1.1K

Authors

7.2K

  1. SW
    Sumio Watanabe

    Tokyo Institute of Technology, Japan

    9 publications · 544 citations

    9

    h-index

  2. AZ
    Anding Zhu

    University College Dublin, Ireland

    8 publications · 346 citations

    8

    h-index

  3. PV
    Paul Vitányi

    Centrum Wiskunde & Informatica, Netherlands

    8 publications · 722 citations

    8

    h-index

  4. JR
    J. Rissanen

    IBM (United States), United States

    7 publications · 2.5K citations

    7

    h-index

  5. HV
    Hoshin V. Gupta

    University of Arizona, United States

    6 publications · 1.4K citations

    6

    h-index

1–5 of 7.2K

Venues

  1. arXiv (Cornell University)

    Repository · 151 publications · 10.2K citations

    47

    h-index

  2. Water Resources Research

    31 publications · 5.3K citations

    26

    h-index

  3. IEEE Access

    22 publications · 1.7K citations

    18

    h-index

  4. PLoS ONE

    19 publications · 2.2K citations

    17

    h-index

  5. 16

    h-index

1–5