• Mathematics, Computer Science
  • Published in NeurIPS 2017

Faithful Inversion of Generative Models for Effective Amortized Inference

@inproceedings{Webb2017FaithfulIO,
  title={Faithful Inversion of Generative Models for Effective Amortized Inference},
  author={Stefan Webb and Adam Golinski and Robert Zinkov and Siddharth Narayanaswamy and Tom Rainforth and Yee Whye Teh and Frank Wood},
  booktitle={NeurIPS},
  year={2017}
}
Inference amortization methods share information across multiple posterior-inference problems, allowing each to be carried out more efficiently. Generally, they require the inversion of the dependency structure in the generative model, as the modeller must learn a mapping from observations to distributions approximating the posterior. Previous approaches have involved inverting the dependency structure in a heuristic way that fails to capture these dependencies correctly, thereby limiting the… CONTINUE READING
28
Twitter Mentions

References

Publications referenced by this paper.
SHOWING 1-7 OF 7 REFERENCES

MADE: Masked Autoencoder for Distribution Estimation

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Learning Stochastic Inverses

VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Adam: A Method for Stochastic Optimization

VIEW 1 EXCERPT

Semisupervised learning with deep generative models

  • Kingma, P Diederik, +5 authors Max
  • In Advances in Neural Information Processing Systems,
  • 2014
VIEW 1 EXCERPT