Concepedia

Multi-task Generalization Bounds

Multi-Task Generalization Bounds is a theoretical framework in machine learning that characterizes the upper limits on the generalization error of a model trained to perform multiple related tasks simultaneously, by analyzing how task similarity and inductive bias jointly influence the model’s ability to generalize across tasks.

10

Publications

756

Citations

21

Authors

19

Institutions

Publications per year

2017–2026

3

Parents

Publications

10

Curriculum learning of multiple tasks

Anastasia Pentina, Viktoriia Sharmanska, Christoph H. Lampert · 2015 · 233 citations

, , +13

Regularization techniques for learning with matrices

Sham M. Kakade, Shai Shalev‐Shwartz, Ambuj Tewari · 2016 · 171 citations

, , +14

Algorithm-Dependent Generalization Bounds for Multi-Task Learning

Tongliang Liu, Dacheng Tao, Mingli Song et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 133 citations

, , +11

Multi-Task Learning and Algorithmic Stability

Yu Zhang · Proceedings of the AAAI Conference on Artificial Intelligence · 2015 · 51 citations · Full text

, , +10

Learning Multiple Tasks using Shared Hypotheses

Koby Crammer, Yishay Mansour · 2012 · 48 citations

, , +17

1–5 of 10

Authors

21

  1. MG
    Michael Georgiopoulos

    University of Central Florida, United States

    1 publications · 11 citations

    1

    h-index

  2. SM
    Sham M. Kakade

    Microsoft (United States), United States

    1 publications · 171 citations

    1

    h-index

  3. MB
    Maria-Florina Balcan

    Carnegie Mellon University, United States

    1 publications · 34 citations

    1

    h-index

  4. TL
    Tongliang Liu

    The University of Sydney, Australia

    1 publications · 133 citations

    1

    h-index

  5. SJ
    Stephen J. Maybank

    Birkbeck, University of London, United Kingdom

    1 publications · 133 citations

    1

    h-index

1–5 of 21

Institutions

19

  1. Centre for Quantum Computation and Communication Technology

    Sydney, Australia

    1 h-index

    2 publications

    266 citations

  2. Microsoft Research New England (United States)

    Cambridge, United States

    1 h-index

    1 publications

    171 citations

  3. Hong Kong Baptist University

    Hong Kong, Hong Kong

    1 h-index

    1 publications

    51 citations

  4. Microsoft (United States)

    Redmond, United States

    1 h-index

    1 publications

    171 citations

  5. Royal Holloway University of London

    Egham, United Kingdom

    1 h-index

    1 publications

    24 citations

  6. Birkbeck, University of London

    London, United Kingdom

    1 h-index

    1 publications

    133 citations

  7. Tel Aviv University

    Tel Aviv, Israel

    1 h-index

    1 publications

    48 citations

  8. Institute of Science and Technology Austria

    Klosterneuburg, Austria

    1 h-index

    3 publications

    699 citations

1–8 of 19

Venues

  1. arXiv (Cornell University)

    Repository · 2 publications · 58 citations

    2

    h-index

  2. 1

    h-index

  3. Neural Information Processing Systems

    Conference · 1 publications · 28 citations

    1

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 51 citations

    1

    h-index

  5. 1

    h-index

1–5