Bounds on approximate steepest descent for likelihood maximization in exponential families

@article{CesaBianchi1994BoundsOA,
  title={Bounds on approximate steepest descent for likelihood maximization in exponential families},
  author={Nicol{\`o} Cesa-Bianchi and Anders Krogh and Manfred K. Warmuth},
  journal={IEEE Trans. Information Theory},
  year={1994},
  volume={40},
  pages={1215-1218}
}
An approximate steepest descent strategy converging, in families of regular exponential densities, to maximum likelihood estimates of density functions is described. These density estimates are also obtained by an application of the principle of minimum relative entropy subject to empirical constraints. We prove tight bounds on the increase of the log-likelihood at each iteration of our strategy for families of exponential densities whose log-densities are spanned by a set of bounded basis… CONTINUE READING
9 Citations
3 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-3 of 3 references

Fundamentals of Statistical Exponential Families, volume 9 of Lecture Notes - Monograph Series

  • L. D. Brown
  • Institute of Math. Stat.,
  • 1986
3 Excerpts

Exponential models, maximum likelihood estimation, and the Haar condition

  • B. R. Crain
  • Journal of the American Statistical Association,
  • 1976
2 Excerpts

Similar Papers

Loading similar papers…