Accuracy-pruning Trade-off

Accuracy-Pruning Trade-Off is a theoretical construct in machine learning that characterizes the inverse relationship between the extent of model parameter removal during pruning and the resulting degradation in predictive performance, distinguishing it from other pruning-related metrics by specifically quantifying the balance between model compactness and functional fidelity.

118

Publications

9.1K

Citations

341

Authors

135

Institutions

Publications per year

2017–2026

76

Authors

341

  1. PM
    Pavlo Molchanov

    Nvidia (United States), United States

    3 publications · 1.8K citations

    4

    h-index

  2. YY
    Yi Yang

    University of Technology Sydney, Australia

    3 publications · 1.3K citations

    3

    h-index

  3. YH
    Yang He

    University of Technology Sydney, Australia

    3 publications · 1.3K citations

    3

    h-index

  4. PG
    Paolo Garza

    Politecnico di Torino, Italy

    3 publications · 225 citations

    3

    h-index

  5. DJ
    David Jensen

    University of Massachusetts Amherst, United States

    3 publications · 102 citations

    3

    h-index

1–5 of 341

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 4.1K citations

    22

    h-index

  2. 3

    h-index

  3. International Conference on Learning Representations

    Conference · 2 publications · 265 citations

    2

    h-index

  4. Machine Learning

    2 publications · 81 citations

    2

    h-index

  5. Knowledge-Based Systems

    2 publications · 107 citations

    2

    h-index

1–5