Corpus ID: 211296260

Variational Hyper RNN for Sequence Modeling

@article{Deng2020VariationalHR,
  title={Variational Hyper RNN for Sequence Modeling},
  author={Ruizhi Deng and Yanshuai Cao and Bo Chang and Leonid Sigal and Greg Mori and Marcus A. Brubaker},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.10501}
}
  • Ruizhi Deng, Yanshuai Cao, +3 authors Marcus A. Brubaker
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence. Our method uses temporal latent variables to capture information about the underlying data pattern and dynamically decodes the latent information into modifications of weights of the base decoder and recurrent model. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 28 REFERENCES

    Disentangled behavioral representations

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Filtering Variational Objectives

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    HyperNetworks

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Importance Weighted Autoencoders

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Auto-Encoding Variational Bayes

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A Neural Stochastic Volatility Model

    VIEW 1 EXCERPT

    Attention is All you Need

    VIEW 2 EXCERPTS

    Bayesian Hypernetworks

    VIEW 3 EXCERPTS