Information decomposition on structured space

@article{Sugiyama2016InformationDO,
  title={Information decomposition on structured space},
  author={Mahito Sugiyama and Hiroyuki Nakahara and Koji Tsuda},
  journal={2016 IEEE International Symposium on Information Theory (ISIT)},
  year={2016},
  pages={575-579}
}
  • Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda
  • Published 2016
  • Computer Science, Mathematics
  • 2016 IEEE International Symposium on Information Theory (ISIT)
  • We build information geometry for a partially ordered set of variables and define the orthogonal decomposition of information theoretic quantities. The natural connection between information geometry and order theory leads to efficient decomposition algorithms. This generalization of Amari's seminal work on hierarchical decomposition of probability distributions on event combinations enables us to analyze high-order statistical interactions arising in neuroscience, biology, and machine learning… CONTINUE READING

    Figures and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 17 REFERENCES

    Information geometry on hierarchy of probability distributions

    VIEW 2 EXCERPTS

    Nonnegative Decomposition of Multivariate Information

    Information-Geometric Measure for Neural Spikes

    An Introduction to Lattices and Order

    VIEW 1 EXCERPT
    HIGHLY INFLUENTIAL