Corpus ID: 57759376

Dirichlet Variational Autoencoder

@article{Joo2018DirichletVA,
  title={Dirichlet Variational Autoencoder},
  author={Weonyoung Joo and Wonsung Lee and Sungrae Park and Il-Chul Moon},
  journal={ArXiv},
  year={2018},
  volume={abs/1901.02739}
}
  • Weonyoung Joo, Wonsung Lee, +1 author Il-Chul Moon
  • Published in ArXiv 2018
  • Mathematics, Computer Science
  • This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a component of the Dirichlet distribution, with the inverse Gamma CDF approximation. Additionally, we reshape the component collapsing issue by investigating two problem sources, which… CONTINUE READING

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

    1
    Twitter Mention

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    Continual Unsupervised Representation Learning

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Product Kanerva Machines: Factorized Bayesian Memory

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 29 REFERENCES

    Stick-Breaking Variational Autoencoders

    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Latent Dirichlet Allocation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Autoencoding Variational Inference For Topic Models

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    Neural Variational Inference for Text Processing

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Categorical Reparameterization with Gumbel-Softmax

    VIEW 2 EXCERPTS