Sample Complexity

Sample Complexity is the minimum number of training samples required for a learning algorithm to achieve a specified level of performance with high probability, distinguishing it from related measures of computational or model complexity by focusing specifically on the dependence of generalization on sample size within the framework of supervised learning.

1.1K

Publications

89.5K

Citations

2.4K

Authors

598

Institutions

Publications per year

2017–2026

593

Authors

2.4K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    20 publications · 9K citations

    17

    h-index

  2. SM
    Sham M. Kakade

    Microsoft (United States), United States

    22 publications · 984 citations

    16

    h-index

  3. MI
    Michael I. Jordan

    University of California, Berkeley, United States

    19 publications · 1.8K citations

    16

    h-index

  4. BR
    Benjamin Recht

    University of California, Berkeley, United States

    17 publications · 1.3K citations

    15

    h-index

  5. YC
    Yuejie Chi

    Carnegie Mellon University, United States

    15 publications · 856 citations

    14

    h-index

1–5 of 2.4K

Venues

  1. arXiv (Cornell University)

    Repository · 403 publications · 34.9K citations

    67

    h-index

  2. IEEE Transactions on Information Theory

    27 publications · 2.7K citations

    21

    h-index

  3. Neural Information Processing Systems

    Conference · 29 publications · 912 citations

    18

    h-index

  4. IEEE Transactions on Signal Processing

    24 publications · 960 citations

    17

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 18 publications · 963 citations

    16

    h-index

1–5