Corpus ID: 211296419

Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows

@article{Deng2020ModelingCS,
  title={Modeling Continuous Stochastic Processes with Dynamic Normalizing Flows},
  author={Ruizhi Deng and Bo Chang and Marcus A. Brubaker and Greg Mori and Andreas M. Lehrmann},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.10516}
}
  • Ruizhi Deng, Bo Chang, +2 authors Andreas M. Lehrmann
  • Published in ArXiv 2020
  • Mathematics, Computer Science
  • Normalizing flows transform a simple base distribution into a complex target distribution and have proved to be powerful models for data generation and density estimation. In this work, we propose a novel type of normalizing flow driven by a differential deformation of the continuous-time Wiener process. As a result, we obtain a rich time series model whose observable process inherits many of the appealing properties of its base process, such as efficient computation of likelihoods and… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    Neural Controlled Differential Equations for Irregular Time Series

    VIEW 4 EXCERPTS
    CITES RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 49 REFERENCES

    Neural Ordinary Differential Equations

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Importance Weighted Autoencoders

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A Recurrent Latent Variable Model for Sequential Data

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Auto-Encoding Variational Bayes

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Normalizing Flows: An Introduction and Review of Current Methods.

    VIEW 1 EXCERPT

    Attentive Neural Processes

    VIEW 2 EXCERPTS