Corpus ID: 59842895

A Differentiable Gaussian-like Distribution on Hyperbolic Space for Gradient-Based Learning

@article{Nagano2019ADG,
  title={A Differentiable Gaussian-like Distribution on Hyperbolic Space for Gradient-Based Learning},
  author={Yoshihiro Nagano and Shoichiro Yamaguchi and Yasuhiro Fujita and Masanori Koyama},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.02992}
}
  • Yoshihiro Nagano, Shoichiro Yamaguchi, +1 author Masanori Koyama
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure. [...] Key Method Also, we can sample from this hyperbolic probability distribution without resorting to auxiliary means like rejection sampling. As applications of our distribution, we develop a hyperbolic-analog of variational autoencoder and a method of probabilistic word embedding on hyperbolic space. We demonstrate the efficacy of our distribution on various datasets…Expand Abstract
    Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders
    • 24
    • Highly Influenced
    • Open Access
    Hierarchical Representations with Poincaré Variational Auto-Encoders
    • 15
    • Highly Influenced
    • Open Access
    Mixed-curvature Variational Autoencoders
    • 7
    • Highly Influenced
    • Open Access
    Poincaré Wasserstein Autoencoder
    • 13
    • Open Access
    Variational Autoencoders with Riemannian Brownian Motion Priors
    • 5
    • Open Access
    Increasing Expressivity of a Hyperspherical VAE
    • 1
    • Open Access
    Increasing Expressivity of a Hyperspherical VAE

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES
    Auto-Encoding Variational Bayes
    • 9,051
    • Open Access
    Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
    • 18,716
    • Highly Influential
    • Open Access
    Poincaré Embeddings for Learning Hierarchical Representations
    • 373
    • Highly Influential
    • Open Access
    Distributed Representations of Words and Phrases and their Compositionality
    • 18,690
    • Open Access
    Stochastic Backpropagation and Approximate Inference in Deep Generative Models
    • 2,684
    • Open Access
    Categorical Reparameterization with Gumbel-Softmax
    • 1,352
    • Open Access
    Representation Tradeoffs for Hyperbolic Embeddings
    • 106
    • Highly Influential
    • Open Access
    Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
    • 107
    • Open Access
    A Kernel Two-Sample Test
    • 1,666
    • Open Access