Corpus ID: 5040612

Sampling the Riemann-Theta Boltzmann Machine

@article{Carrazza2018SamplingTR,
  title={Sampling the Riemann-Theta Boltzmann Machine},
  author={Stefano Carrazza and Daniel Krefl},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.07768}
}
  • Stefano Carrazza, Daniel Krefl
  • Published in ArXiv 2018
  • Mathematics, Computer Science
  • We show that the visible sector probability density function of the Riemann-Theta Boltzmann machine corresponds to a gaussian mixture model consisting of an infinite number of component multi-variate gaussians. The weights of the mixture are given by a discrete multi-variate gaussian over the hidden state space. This allows us to sample the visible sector density function in a straight-forward manner. Furthermore, we show that the visible sector probability density function possesses an affine… CONTINUE READING

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

    13
    Twitter Mentions

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.

    Modelling conditional probabilities with Riemann-Theta Boltzmann Machines

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES

    Riemann-Theta Boltzmann Machine

    VIEW 7 EXCERPTS

    Computing Riemann theta functions

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Variational Inference with Normalizing Flows

    VIEW 2 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Adversarial Nets

    VIEW 2 EXCERPTS

    Sampling from discrete Gaussians for lattice-based cryptography on a constrained device

    VIEW 1 EXCERPT

    Auto-Encoding Variational Bayes

    VIEW 2 EXCERPTS

    How to Use a Short Basis: Trapdoors for Hard Lattices and New Cryptographic Constructions

    • C. Gentry, V. Vaikuntanathan, C. Peikert
    • 2008
    • 2008

    Completely Derandomized Self-Adaptation in Evolution Strategies

    VIEW 1 EXCERPT