Multiscale likelihood analysis and complexity penalized estimation

@article{Kolaczyk2004MultiscaleLA,
  title={Multiscale likelihood analysis and complexity penalized estimation},
  author={E. Kolaczyk and R. Nowak},
  journal={Annals of Statistics},
  year={2004},
  volume={32},
  pages={500-527}
}
  • E. Kolaczyk, R. Nowak
  • Published 2004
  • Mathematics
  • Annals of Statistics
  • We describe here a framework for a certain class of multiscale likelihood factorizations wherein, in analogy to a wavelet decomposition of an L 2 function, a given likelihood function has an alternative representation as a product of conditional densities reflecting information in both the data and the parameter vector localized in position and scale. The framework is developed as a set of sufficient conditions for the existence of such factorizations, formulated in analogy to those underlying… CONTINUE READING
    128 Citations
    Multiscale Density Estimation
    • 9
    • PDF
    Noisy Matrix Completion Under Sparse Factor Models
    • 30
    • PDF
    Multiscale Poisson Intensity and Density Estimation
    • R. Willett, R. Nowak
    • Mathematics, Computer Science
    • IEEE Transactions on Information Theory
    • 2007
    • 134
    • PDF
    Multiscale Poisson data smoothing
    • 53
    • PDF
    Error bounds for maximum likelihood matrix completion under sparse factor models
    • 6
    • PDF
    Unbalanced Haar Technique for Nonparametric Function Estimation
    • 61
    • PDF
    Varying complexity in tree-structured image distribution models
    • 9
    • PDF
    Data-driven wavelet-Fisz methodology for nonparametric function estimation
    • 19
    • PDF

    References

    SHOWING 1-10 OF 30 REFERENCES
    A statistical multiscale framework for Poisson inverse problems
    • 132
    Bayesian Multiscale Models for Poisson Processes
    • 129
    Estimation of mixture models
    • 77
    • PDF
    Nonlinear approximation
    • 821
    • PDF
    Mixture Density Estimation
    • 246
    • PDF
    CART AND BEST-ORTHO-BASIS: A CONNECTION'
    • 233
    • PDF