Variational Dropout

Variational Dropout is a variational inference method that extends Bayesian dropout by treating dropout rates as learnable parameters within a probabilistic framework, enabling automatic optimization of sparsity during training through stochastic gradient variational inference.

67

Publications

5K

Citations

207

Authors

106

Institutions

Publications per year

2017–2026

56

Authors

207

  1. ZG
    Zoubin Ghahramani

    University of Cambridge, United Kingdom

    4 publications · 1.8K citations

    4

    h-index

  2. YG
    Yarin Gal

    University of Oxford, United Kingdom

    4 publications · 1.8K citations

    4

    h-index

  3. JC
    Jaemin Cho

    University of North Carolina at Chapel Hill, United States

    2 publications · 120 citations

    2

    h-index

  4. NK
    Nikolaus Kriegeskorte

    MRC Cognition and Brain Sciences Unit, United Kingdom

    2 publications · 28 citations

    2

    h-index

  5. ES
    Ewa Szczurek

    University of Warsaw, Poland

    2 publications · 149 citations

    2

    h-index

1–5 of 207

Venues

  1. arXiv (Cornell University)

    Repository · 18 publications · 1.6K citations

    14

    h-index

  2. Sensors

    2 publications · 47 citations

    2

    h-index

  3. Bioinformatics

    2 publications · 105 citations

    2

    h-index

  4. International Conference on Artificial Intelligence and Statistics

    Conference · 2 publications · 154 citations

    2

    h-index

  5. Neural Networks

    2 publications · 60 citations

    2

    h-index

1–5