Meta-regularization

Meta-Regularization is a meta-learning framework that imposes structural constraints on the learning algorithm’s inductive bias by regularizing the meta-learned prior knowledge transfer across tasks to enhance generalization.

25

Publications

2.3K

Citations

71

Authors

32

Institutions

Publications per year

2017–2026

23

Authors

71

  1. CF
    Chelsea Finn

    University of California, Berkeley, United States

    2 publications · 115 citations

    3

    h-index

  2. JR
    Janarthanan Rajendran

    University of Michigan, United States

    2 publications · 50 citations

    2

    h-index

  3. MZ
    Mingyuan Zhou

    The University of Texas at Austin, United States

    2 publications · 115 citations

    2

    h-index

  4. SL
    Sergey Levine

    University of California, Berkeley, United States

    2 publications · 115 citations

    2

    h-index

  5. MY
    Mingzhang Yin

    The University of Texas at Austin, United States

    2 publications · 115 citations

    2

    h-index

1–5 of 71

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 122 citations

    4

    h-index

  2. International Conference on Learning Representations

    Conference · 2 publications · 64 citations

    2

    h-index

  3. 1

    h-index

  4. Neural Information Processing Systems

    Conference · 1 publications · 404 citations

    1

    h-index

  5. Journal of Biomolecular NMR

    1 publications · 74 citations

    1

    h-index

1–5