Combining evolution strategy and gradient descent method for discriminative learning of bayesian classifiers

@inproceedings{Chen2009CombiningES,
  title={Combining evolution strategy and gradient descent method for discriminative learning of bayesian classifiers},
  author={Xuefeng Chen and Xiabi Liu and Yunde Jia},
  booktitle={GECCO},
  year={2009}
}
The optimization method is one of key issues in discriminative learning of pattern classifiers. This paper proposes a hybrid approach of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and the gradient decent method for optimizing Bayesian classifiers under the SOFT target based Max-Min posterior Pseudo-probabilities (Soft-MMP) learning framework. In our hybrid optimization approach, the weighted mean of the parent population in the CMA-ES is adjusted by exploiting the gradient… CONTINUE READING
4 Citations
8 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-8 of 8 references

An analysis of mutative σ-self-Adaptation on linear fitness functions

  • N. Hansen
  • Evolutionary Computation,
  • 2006
Highly Influential
11 Excerpts

Image Classification Using the Max-Min Posterior Pseudo- Probabilities Method

  • X. B. Liu, Y. D. Jia, X. F. Chen, Y. Deng, H. Fu
  • Technical Report, BIT-CS-20080001. Beijing…
  • 2008
Highly Influential
4 Excerpts

Similar Papers

Loading similar papers…