Filling the gaps: Gaussian mixture models from noisy, truncated or incomplete samples

@article{Melchior2018FillingTG,
  title={Filling the gaps: Gaussian mixture models from noisy, truncated or incomplete samples},
  author={P. Melchior and A. Goulding},
  journal={Astron. Comput.},
  year={2018},
  volume={25},
  pages={183-194}
}
  • P. Melchior, A. Goulding
  • Published 2018
  • Computer Science, Mathematics, Physics
  • Astron. Comput.
  • Astronomical data often suffer from noise and incompleteness. We extend the common mixtures-of-Gaussians density estimation approach to account for situations with a known sample incompleteness by simultaneous imputation from the current model. The method, called GMMis, generalizes existing Expectation-Maximization techniques for truncated data to arbitrary truncation geometries and probabilistic rejection processes, as long as they can be specified and do not depend on the density itself. The… CONTINUE READING
    10 Citations
    Unsupervised Learning of Mixture Models with a Uniform Background Component
    • 1
    • PDF
    Semiparametric density testing in the contamination model
    • 1
    • PDF
    Unsupervised automatic dataset repair
    • 1
    • PDF

    References

    SHOWING 1-10 OF 14 REFERENCES
    Finite Mixture Models
    • 2,684
    Split and Merge EM Algorithm for Improving Gaussian Mixture Density Estimates
    • 74
    • Highly Influential
    • PDF
    Linearly Combining Density Estimators via Stacking
    • 121
    • PDF
    EM algorithms for multivariate Gaussian mixture models with truncated and censored data
    • 100
    • PDF
    Fitting mixture models to grouped and truncated data via the EM algorithm.
    • 132
    EM algorithms for Gaussian mixtures with split-and-merge operation
    • 147
    ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM
    • 3,052
    • PDF