Near Universal Consistency of the Maximum Pseudolikelihood Estimator for Discrete Models

  title={Near Universal Consistency of the Maximum Pseudolikelihood Estimator for Discrete Models},
  author={Hien Duy Nguyen},
  journal={arXiv: Methodology},
  • H. Nguyen
  • Published 16 January 2017
  • Mathematics
  • arXiv: Methodology

Reliability of decisions based on tests: Fourier analysis of Boolean decision functions

It is concluded that a weighted sum score has desirable properties that fit with test theory and is observable, has the property that a decision is stable (reliable), and satisfies Rousseau's criterion that the input should match the decision.

A model and a numerical scheme for the description of distribution and abundance of individuals

We introduce a model in the context of ecology that can be used to describe the distribution and abundance of individuals when data from field work is extremely limited (for example, in the case of

Relations between Networks, Regression, Partial Correlation, and the Latent Variable Model

A connection between the ULVM and the GGM is introduced and it is proved that the authors find a fully-connected and not an empty network associated with a ULVM, and the relation between GGMs and linear regression is used to show that the partial correlation indeed does not remove the common variance.

The fully visible Boltzmann machine and the Senate of the 45th Australian Parliament in 2016

Using publicly available Senate voting data in 2016, quantitatively analyzed two aspects of the Senate and utilized the fully-visible Boltzmann machine (FVBM) model to reveal the interaction structures within the Australian Senate.



Asymptotic Normality of the Maximum Pseudolikelihood Estimator for Fully Visible Boltzmann Machines

  • H. NguyenI. Wood
  • Mathematics
    IEEE Transactions on Neural Networks and Learning Systems
  • 2016
It is proved that MPLE also yields an asymptotically normal parameter estimator, which provides a closed-form alternative to the current methods that require Monte Carlo simulation or resampling.

Nearly universal consistency of maximum likelihood in discrete models

Convex models, MLE and misspecification

We analyze the asymptotic behavior of maximum likelihood estimators (MLE) in convex dominated models when the true distribution generating the independent data does not necessarily belong to the


SUMMARY. In some estimation problems the joint likelihood involves an awkward nor malizing function of the parameters. In such cases the method of maximum likelihood is liable to be inconvenient. An

A note on pseudolikelihood constructed from marginal densities

The asymptotic properties of formal maximum likelihood estimators in applications in which only a single qx1 vector of observations is observed are examined, and conditions under which consistent estimators of parameters result from the approximate likelihood using only pairwise joint distributions are studied.

Composite likelihood estimation for restricted Boltzmann machines

This paper proposes a composite likelihood method and investigates its properties and applies this to restricted Boltzmann machines.

A Block Successive Lower-Bound Maximization Algorithm for the Maximum Pseudo-Likelihood Estimation of Fully Visible Boltzmann Machines

An algorithm for the MPLE of FVBMs based on the block successive lower-bound maximization (BSLM) principle is presented and it is shown that the BSLM algorithm monotonically increases the pseudo-likelihood values and that the sequence of B SLM estimates converges to the unique global maximizer of the pseudo -likelihood function.


0 and ai. The parameter 0, upon which all the distributions depend, is called "structural"; the parameters {aiI} are called "incidental". Throughout this paper we shall assume that the Xi, are

Composite Likelihood Methods

This issue includes two long overview papers, one of which is devoted to applications in statistical genetics; several papers developing new theory for inference based on composite likelihood; new results in the application of composite likelihood to time series, spatial processes, longitudinal data and missing data.

Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines

It is shown that the old principle of pseudolikelihood estimation provides an estimator that is computationally very simple yet statistically consistent in the basic case of fully visible Boltzmann machines.