Online Meta-learning

Online Meta-Learning is a meta-learning framework that dynamically updates the meta-learner in a sequential, incremental manner as tasks arrive over time, distinguishing itself from batch meta-learning approaches by its continuous adaptation to new tasks without reprocessing past data.

95

Publications

4.1K

Citations

332

Authors

133

Institutions

Publications per year

2017–2026

80

Authors

332

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    5 publications · 662 citations

    5

    h-index

  2. SP
    Sangwoo Park

    King's College School, United Kingdom

    3 publications · 116 citations

    3

    h-index

  3. CF
    Chelsea Finn

    University of California, Berkeley, United States

    3 publications · 502 citations

    3

    h-index

  4. OS
    Osvaldo Simeone

    New Jersey Institute of Technology, United States

    3 publications · 116 citations

    3

    h-index

  5. MK
    Mikhail Khodak

    Princeton University, United States

    3 publications · 106 citations

    3

    h-index

1–5 of 332

Venues

  1. arXiv (Cornell University)

    Repository · 21 publications · 1K citations

    13

    h-index

  2. IEEE Transactions on Wireless Communications

    2 publications · 174 citations

    2

    h-index

  3. 2

    h-index

  4. Neural Information Processing Systems

    Conference · 2 publications · 45 citations

    2

    h-index

  5. IEEE Transactions on Cybernetics

    1 publications · 69 citations

    1

    h-index

1–5