Mutual information and posterior estimates in channels of exponential family type

@article{Raginsky2009MutualIA,
  title={Mutual information and posterior estimates in channels of exponential family type},
  author={Maxim Raginsky and Todd P. Coleman},
  journal={2009 IEEE Information Theory Workshop},
  year={2009},
  pages={399-403}
}
Recently, there has been a lot of interest in the connections between information-theoretic and estimation-theoretic properties of various noisy channel models. For example, Guo, Shamai, and Verdu´ have shown that mutual information in Gaussian channels is related in a simple way to minimum mean-square error, regardless of the input distribution. In this paper, we consider the class of E-type channels, i.e., additive noise channels induced by an exponential family of distributions. We derive… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 19 REFERENCES

Representation of Mutual Information Via Input Estimates

  • IEEE Transactions on Information Theory
  • 2007
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

A Variational Approach to Nonlinear Estimation

  • SIAM J. Control and Optimization
  • 2003
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Capacity of queues via point-process channels

  • IEEE Transactions on Information Theory
  • 2006
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Mutual information and minimum mean-square error in Gaussian channels

  • IEEE Transactions on Information Theory
  • 2004
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Bits through queues

  • IEEE Trans. Information Theory
  • 1994
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Additive non-Gaussian noise channels: mutual information and conditional mean estimation

  • Proceedings. International Symposium on Information Theory, 2005. ISIT 2005.
  • 2005
VIEW 1 EXCERPT