Regularization-based Pruning

Regularization-Based Pruning is a model compression technique within neural network pruning that belongs to the broader category of regularization methods, distinguished by its incorporation of structured or sparsity-inducing penalties during training to progressively steer model weights toward zero, thereby enabling the systematic removal of redundant or less significant parameters.

63

Publications

3.3K

Citations

207

Authors

83

Institutions

Publications per year

2017–2026

47

Authors

207

  1. LK
    Lars Kai Hansen

    Technical University of Denmark, Denmark

    4 publications · 120 citations

    4

    h-index

  2. ZM
    Zelda Mariet

    Massachusetts Institute of Technology, United States

    3 publications · 82 citations

    3

    h-index

  3. NW
    Naiyan Wang

    University of Chinese Academy of Sciences, China

    3 publications · 131 citations

    3

    h-index

  4. JL
    Jan Larsen

    Technical University of Denmark, Denmark

    3 publications · 61 citations

    3

    h-index

  5. RJ
    Rongrong Ji

    Xiamen University, China

    3 publications · 452 citations

    3

    h-index

1–5 of 207

Venues

  1. arXiv (Cornell University)

    Repository · 14 publications · 451 citations

    11

    h-index

  2. 5

    h-index

  3. IEEE Access

    3 publications · 104 citations

    3

    h-index

  4. IEEE Transactions on Cybernetics

    2 publications · 108 citations

    2

    h-index

  5. 2

    h-index

1–5