Corpus ID: 53720503

Latent Projection BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights

@article{Pradier2018LatentPB,
  title={Latent Projection BNNs: Avoiding weight-space pathologies by learning latent representations of neural network weights},
  author={Melanie F. Pradier and Weiwei Pan and Jiayu Yao and Soumya Ghosh and Finale Doshi-Velez},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.07006}
}
  • Melanie F. Pradier, Weiwei Pan, +2 authors Finale Doshi-Velez
  • Published in ArXiv 2018
  • Mathematics, Computer Science
  • As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing uncertainty over the parameters of these models is challenging because of the high dimensionality and complex correlations of the network parameter space. This paper introduces a novel variational inference framework for Bayesian neural networks that (1) encodes… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    7
    Twitter Mentions

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    The Case for Bayesian Deep Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Towards a Kernel based Physical Interpretation of Model Uncertainty

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES

    Variational Dropout and the Local Reparameterization Trick

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Black Box Variational Inference

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Weight Uncertainty in Neural Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Ensemble Sampling

    Implicit Weight Uncertainty in Neural Networks

    VIEW 1 EXCERPT