Pith. sign in

Variational inference: A review for statisticians

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

method 1

citation-polarity summary

fields

stat.ML 1

years

2019 1

verdicts

ACCEPT 1

roles

method 1

polarities

support 1

representative citing papers

On the Expressiveness of Approximate Inference in Bayesian Neural Networks

stat.ML · 2019-09-02 · accept · novelty 8.0

For single-hidden-layer ReLU Bayesian neural networks, mean-field Gaussian and Monte Carlo dropout posteriors provably cannot express higher predictive variance between well-separated low-variance regions, and this limitation persists empirically in deep networks despite a universality theorem.

citing papers explorer

Showing 1 of 1 citing paper.

  • On the Expressiveness of Approximate Inference in Bayesian Neural Networks stat.ML · 2019-09-02 · accept · none · ref 5

    For single-hidden-layer ReLU Bayesian neural networks, mean-field Gaussian and Monte Carlo dropout posteriors provably cannot express higher predictive variance between well-separated low-variance regions, and this limitation persists empirically in deep networks despite a universality theorem.