Optimization-based Meta-learning

Optimization-Based Meta-Learning is a meta-learning approach that employs optimization procedures as the primary mechanism to enable rapid adaptation to new tasks by learning an effective initialization or update rule through experience.

85

Publications

5.2K

Citations

328

Authors

146

Institutions

Publications per year

2017–2026

72

Authors

328

  1. XG
    Xiaoxiao Guo

    IBM (United States), United States

    3 publications · 323 citations

    3

    h-index

  2. MY
    Mo Yu

    IBM (United States), United States

    3 publications · 323 citations

    3

    h-index

  3. YC
    Yu Cheng

    Tsinghua University, China

    3 publications · 323 citations

    3

    h-index

  4. FM
    Fei Mi

    École Polytechnique Fédérale de Lausanne, Switzerland

    2 publications · 100 citations

    2

    h-index

  5. YY
    Yuxiang Yang

    Google (United States), United States

    2 publications · 90 citations

    2

    h-index

1–5 of 328

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 346 citations

    6

    h-index

  2. Neurocomputing

    5 publications · 295 citations

    5

    h-index

  3. IEEE Access

    4 publications · 123 citations

    4

    h-index

  4. Pattern Recognition

    3 publications · 227 citations

    3

    h-index

  5. Lecture notes in computer science

    LNCS · Book series · 2 publications · 28 citations

    2

    h-index

1–5