Kullback-leibler Divergence

Kullback-Leibler Divergence is a non-symmetric information-theoretic measure of the difference between two probability distributions, quantifying the expected number of extra bits required to code samples from one distribution when using a coding scheme optimized for another.

2.3K

Publications

175.4K

Citations

5.1K

Authors

1.6K

Institutions

Publications per year

2017–2026

732

Variants

Kl DivergenceKullback-leibler InformationRelative Entropy

Authors

5.1K

  1. FN
    Frank Nielsen

    Sony Computer Science Laboratories, Japan

    21 publications · 864 citations

    16

    h-index

  2. IV
    Igor Vajda

    Czech Academy of Sciences, Institute of Information Theory and Automation, Czechia

    11 publications · 1.1K citations

    11

    h-index

  3. AS
    Abd‐Krim Seghouane

    The University of Melbourne, Australia

    11 publications · 494 citations

    10

    h-index

  4. FK
    Frank K. Soong

    Microsoft Research Asia (China), China

    10 publications · 194 citations

    10

    h-index

  5. ES
    Ehsan S. Soofi

    University of Wisconsin–Milwaukee, United States

    10 publications · 683 citations

    10

    h-index

1–5 of 5.1K

Venues

  1. IEEE Transactions on Information Theory

    63 publications · 10.9K citations

    36

    h-index

  2. IEEE Transactions on Signal Processing

    52 publications · 3.1K citations

    32

    h-index

  3. arXiv (Cornell University)

    Repository · 98 publications · 3.7K citations

    32

    h-index

  4. The Annals of Statistics

    36 publications · 4K citations

    29

    h-index

  5. Entropy

    65 publications · 3.1K citations

    28

    h-index

1–5