Divergence Minimization

Divergence Minimization is a variational inference technique that belongs to the class of optimization approaches used to approximate intractable probability distributions, distinguished by its objective of reducing the discrepancy—measured by a divergence metric such as the Kullback-Leibler divergence—between a tractable variational distribution and the true posterior distribution.

748

Publications

53K

Citations

1.6K

Authors

665

Institutions

Publications per year

2017–2026

262

Authors

1.6K

  1. FN
    Frank Nielsen

    Sony Computer Science Laboratories, Japan

    16 publications · 893 citations

    13

    h-index

  2. LP
    Leandro Pardo

    Universidad Complutense de Madrid, Spain

    16 publications · 344 citations

    13

    h-index

  3. RN
    Richard Nock

    Sony Computer Science Laboratories, Japan

    9 publications · 470 citations

    9

    h-index

  4. AG
    Arthur Gretton

    University College London, United Kingdom

    7 publications · 194 citations

    7

    h-index

  5. MC
    Marco Cuturi

    Kyoto University, Japan

    7 publications · 377 citations

    7

    h-index

1–5 of 1.6K

Venues

  1. arXiv (Cornell University)

    Repository · 125 publications · 6.6K citations

    37

    h-index

  2. IEEE Transactions on Information Theory

    22 publications · 2.2K citations

    17

    h-index

  3. Entropy

    20 publications · 873 citations

    16

    h-index

  4. Neural Computation

    11 publications · 7.4K citations

    11

    h-index

  5. 10

    h-index

1–5