Margin Theory

Margin Theory is a theoretical framework in supervised learning that characterizes the generalization performance of classifiers, particularly support vector machines, by the size of the separation (margin) between classes in feature space, distinguishing itself from other learning theories by prioritizing margin maximization as a principle for model robustness and error bounds.

271

Publications

35.4K

Citations

526

Authors

262

Institutions

Publications per year

2017–2026

60

Authors

526

  1. ZZ
    Zhi‐Hua Zhou

    Nanjing University, China

    11 publications · 566 citations

    11

    h-index

  2. RE
    Robert E. Schapire

    AT&T (United States), United States

    8 publications · 4.2K citations

    8

    h-index

  3. TZ
    Teng Zhang

    Nanjing University, China

    7 publications · 285 citations

    7

    h-index

  4. PL
    Peter L. Bartlett

    University of California, Berkeley, United States

    6 publications · 3.3K citations

    6

    h-index

  5. YS
    Yoram Singer

    Hebrew University of Jerusalem, Israel

    5 publications · 2.9K citations

    5

    h-index

1–5 of 526

Venues

  1. arXiv (Cornell University)

    Repository · 29 publications · 1.4K citations

    18

    h-index

  2. The Annals of Statistics

    11 publications · 4.2K citations

    11

    h-index

  3. Neurocomputing

    8 publications · 159 citations

    8

    h-index

  4. Pattern Recognition Letters

    7 publications · 132 citations

    7

    h-index

  5. Neural Computation

    5 publications · 79 citations

    5

    h-index

1–5