Model Trimming

Model Trimming is a methodological contribution in the field of machine learning that systematically reduces the size of a trained model by removing redundant or less critical components to improve computational efficiency while preserving performance.

21

Publications

1.9K

Citations

51

Authors

27

Institutions

Publications per year

2017–2026

5

Authors

51

  1. JJ
    Jana Jurečková

    Charles University, Czechia

    2 publications · 35 citations

    2

    h-index

  2. MB
    Mohit Bansal

    University of North Carolina at Chapel Hill, United States

    1 publications · 23 citations

    1

    h-index

  3. DM
    Douglas M. Hawkins

    University of Minnesota, United States

    1 publications · 81 citations

    1

    h-index

  4. GE
    George E. Backus

    University of California San Diego, United States

    1 publications · 45 citations

    1

    h-index

  5. MT
    Marı́a Teresa Gallegos

    University of Passau, Germany

    1 publications · 25 citations

    1

    h-index

1–5 of 51

Venues

  1. Computational Statistics & Data Analysis

    CSDA · 3 publications · 119 citations

    3

    h-index

  2. arXiv (Cornell University)

    Repository · 2 publications · 767 citations

    2

    h-index

  3. Psychometrika

    1 publications · 69 citations

    1

    h-index

  4. Mathematics of Operations Research

    1 publications · 26 citations

    1

    h-index

  5. Arrow@dit (Dublin Institute of Technology)

    Repository · 1 publications · 15 citations

    1

    h-index

1–5