Evidence Lower Bound

Evidence Lower Bound is a variational objective function that serves as a lower bound on the log-likelihood of observed data, derived by applying Jensen's inequality to the marginal likelihood in order to enable tractable posterior inference in latent variable models.

96

Publications

4.4K

Citations

254

Authors

108

Institutions

Publications per year

2017–2026

80

Authors

254

  1. DD
    David Duvenaud

    University of Toronto, Canada

    6 publications · 346 citations

    6

    h-index

  2. RG
    Roger Grosse

    University of Toronto, Canada

    5 publications · 346 citations

    5

    h-index

  3. MZ
    Mingyuan Zhou

    The University of Texas at Austin, United States

    3 publications · 97 citations

    3

    h-index

  4. BT
    Bangsheng Tang

    Beijing Institute of Technology, China

    3 publications · 774 citations

    3

    h-index

  5. HZ
    Hanning Zhou

    University of Illinois Urbana-Champaign, United States

    3 publications · 774 citations

    3

    h-index

1–5 of 254

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 1.5K citations

    21

    h-index

  2. International Conference on Learning Representations

    Conference · 5 publications · 112 citations

    5

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 3 publications · 43 citations

    3

    h-index

  4. 3

    h-index

  5. IEEE Transactions on Signal Processing

    2 publications · 166 citations

    2

    h-index

1–5