Amortized Variational Inference

Amortized Variational Inference is a variational inference method that learns a global inference network to efficiently approximate posterior distributions across multiple observations by sharing parameters, thereby amortizing the cost of inference over many data points.

47

Publications

4.2K

Citations

149

Authors

71

Institutions

Publications per year

2017–2026

46

Variants

Avi

Authors

149

  1. SE
    Stefano Ermon

    Stanford University, United States

    4 publications · 669 citations

    4

    h-index

  2. ND
    Noah D. Goodman

    Stanford University, United States

    4 publications · 79 citations

    4

    h-index

  3. AM
    Alexander M. Rush

    Harvard University Press, United States

    3 publications · 246 citations

    3

    h-index

  4. DM
    David M. Blei

    Princeton University, United States

    3 publications · 57 citations

    3

    h-index

  5. YW
    Yee Whye Teh

    University of Oxford, United Kingdom

    3 publications · 87 citations

    3

    h-index

1–5 of 149

Venues

  1. arXiv (Cornell University)

    Repository · 20 publications · 2.5K citations

    16

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 3 publications · 327 citations

    3

    h-index

  3. Neural Information Processing Systems

    Conference · 2 publications · 39 citations

    2

    h-index

  4. bioRxiv (Cold Spring Harbor Laboratory)

    Repository · 1 publications · 12 citations

    1

    h-index

  5. Sensors

    1 publications · 13 citations

    1

    h-index

1–5