Identifiability of Modified Power Series Mixtures via Posterior Means

Problems of specification of discrete bivariate statistical models by a modified power series conditional distribution and a regression function are studied. An identifiability result for a wide class of such mixtures with infinite support is obtained. Also the finite support case within a more specific model is considered. Applications for Poisson, (truncated) geometric, and binomial mixtures are given. From the viewpoint of Bayesian analysis unique determination of the prior by a Bayes estimate of the mean for modified power series mixtures is investigated.     

Gauss因果模型中因果效应识别方法的比较

一个Gauss因果模型中常常存在不只一种识别因果效应的方法, 不同的方法对应的估计可能不同. 该文对Pearl等人提出的前门准则, 后门准则,工具变量准则等识别方法的估计精度进行了分析比较, 并给出了相应的模拟结果, 为实践中选择更优的识别准则提供了依据.     

Characterization and Statistical Estimation of a Discriminant Space for Gaussian Mixtures

The problem of classification of a multivariate observation X drawn from a mixture of Gaussian distributions is considered. A linear subspace of the least dimension containing all information about the cluster structure of X is called a discriminant space (DS). Estimation of DS is based on characterizations of DS via projection pursuit with an appropriate projection index. An estimator of DS is obtained merely by applying the projection pursuit with the projection index replaced by its nonparametric estimator. We discuss the asymptotic behavior of the estimator obtained in this way.     

Likelihood Maximization and Moment Matching in Low SNR Gaussian Mixture Models

We derive an asymptotic expansion for the log-likelihood of Gaussian mixture models (GMMs) with equal covariance matrices in the low signal-to-noise regime. The expansion reveals an intimate connection between two types of algorithms for parameter estimation: the method of moments and likelihood optimizing algorithms such as Expectation-Maximization (EM). We show that likelihood optimization in the low SNR regime reduces to a sequence of least squares optimization problems that match the moments of the estimate to the ground truth moments one by one. This connection is a stepping stone towards the analysis of EM and maximum likelihood estimation in a wide range of models. A motivating application for the study of low SNR mixture models is cryo-electron microscopy data, which can be modeled as a GMM with algebraic constraints imposed on the mixture centers. We discuss the application of our expansion to algebraically constrained GMMs, among other example models of interest. © 2022 The Authors. Communications on Pure and Applied Mathematics published by Wiley Periodicals LLC.     

Moment functions of a solution of the diffusion equation with Gaussian random coefficients

We obtain formulas for the expectation and the second moment function of the solution of the Cauchy problem for an inhomogeneous differential heat equation with two phase variables and with independent Gaussian random coefficients.     

Determination of Set-Membership Identifiability Sets

This paper concerns the concept of set-membership identifiability introduced in Jauberthie et al. (Proceedings of the 18th IFAC World Congress. Milan, Italie, 12024–12029, 2011). Given a model, a set-membership identifiable set is a connected set in the parameter domain of the model such that its corresponding trajectories are distinct to trajectories arising from its complementary. For obtaining the so-called set-membership identifiable sets, we propose an algorithm based on interval analysis tools. The proposed algorithm is decomposed into three parts namely mincing, evaluating and regularization (Jaulin et al. in Applied interval analysis, with examples in parameter and state estimation, robust control and robotics. Springer, Londres, 2001). The latter step has been modified in order to obtain guaranteed set-membership identifiable sets. Our algorithm will be tested on two examples.     

Global Identifiability of Differential Models

Many real-world processes and phenomena are modeled using systems of ordinary differential equations with parameters. Given such a system, we say that a parameter is globally identifiable if it can be uniquely recovered from input and output data. The main contribution of this paper is to provide theory, an algorithm, and software for deciding global identifiability. First, we rigorously derive an algebraic criterion for global identifiability (this is an analytic property), which yields a deterministic algorithm. Second, we improve the efficiency by randomizing the algorithm while guaranteeing the probability of correctness. With our new algorithm, we can tackle problems that could not be tackled before. A software based on the algorithm (called SIAN) is available at https://github.com/pogudingleb/SIAN . © 2020 Wiley Periodicals LLC     

Identifiability in linear processes

Probability Theory and Related Fields -     

Consistency of Posterior Mixtures in the Gaussian Family on a Hilbert Space and Its Applications

Majumdar (1994, J. Multivariate Anal.48 87-105) compounds (in the sense of Robbins, 1951, "Proceedings, Second Berkeley Sympos. Math. Statist. Probab.," pp. 131-148, Univ. of California Press, Berkeley) the estimation problem in the mean-parameter family of Gaussian distributions on a real separable infinite dimensional Hilbert space. The question of asymptotic optimality of compound estimators that are Bayes versus a hyperprior mixture of i.i.d. priors on the compound parameter is reduced there, under a compactness restriction on the parameter space, to the question of consistency, in an extended sense, of a certain posterior mixture for the empirical mixture. For mixing hyperpriors with full topological support, that consistency result is obtained in this paper. A corollary of the consistency result is applied to obtain asymptotically optimal decision rules in the empirical Bayes problem involving the mean-parameter Gaussian family and a sufficiently smooth risk function.     

二元一般指数分布的识别性及其参数估计

讨论了一般二元指数分布的识别性问题及参数估计问题.本文证明了两个结论:其一、当只有最大值随机变量的分布已知时,仅一个参数可识别;其二、当可识别最大值的分布已知时,所有参数皆可识别.进一步根据上述结论得到了所有参数的最大似然估计.     

Identifiability for random translations of Poisson processes

Summary A system in which each point of a stationary Poisson process is subjected to a random displacement, the displacements being independently and identically distributed, is considered. It is shown that the displacement distribution is identifiable if we are given a realization of the original process and the corresponding realization of the displaced process but not the linkage between the two.     

Identifiability of intermediate variables on causal paths

We discuss the discovery of causal mechanisms and identifiability of intermediate variables on a causal path. Different from variable selection, we try to distinguish intermediate variables on the causal path from other variables. It is also different from ordinary model selection approaches which do not concern the causal relationships and do not contain unobserved variables. We propose an approach for selecting a causal mechanism depicted by a directed acyclic graph (DAG) with an unobserved variable. We consider several causal networks, and discuss their identifiability by observed data. We show that causal mechanisms of linear structural equation models are not identifiable. Furthermore, we present that causal mechanisms of nonlinear models are identifiable, and we demonstrate the identifiability of causal mechanisms of quadratic equation models. Sensitivity analysis is conducted for the identifiability.     

On the Identifiability of Minimal VARMA Representations

By studying the geometry of relevant Hilbert spaces, we give a characterization of the identifiable standard representations of multivariate ARMA models in terms of the autocovariance function.     

Identifiability at the boundary for first-order terms

Let Ω be a domain in R ⁿ whose boundary is C ¹ if n≥3 or C ^1,β if n=2. We consider a magnetic Schrödinger operator L _{W , q} in Ω and show how to recover the boundary values of the tangential component of the vector potential W from the Dirichlet to Neumann map for L _{W , q} . We also consider a steady state heat equation with convection term Δ+2W·? and recover the boundary values of the convection term W from the Dirichlet to Neumann map. Our method is constructive and gives a stability result at the boundary.     

On the Bayesian Mixture Model and Identifiability

This article is concerned with Bayesian mixture models and identifiability issues. There are two sources of unidentifiability: the well-known likelihood invariance under label switching and the perhaps less well-known parameter identifiability problem. When using latent allocation variables determined by the mixture model, these sources of unidentifiability create arbitrary labeling that renders estimation of the model very difficult. We endeavor to tackle these problems by proposing a prior distribution on the allocations, which provides an explicit interpretation for the labeling by removing gaps with high probability. We propose a Markov chain Monte Carlo (MCMC) estimation method and present supporting illustrations.     

Identifiability of finite mixtures using a new transform

Identifiability of finite mixtures of the following families of distributions are proved: Weibull, normal log, chi, pareto and power function.     

Takagi-Sugeno模糊模型的可辨识性问题

Takagi—Sugeno模糊模型广泛应用于对复杂系统的辨识,但可辨识性问题很少涉及。本文给出在规则数和规则前件确定的情况下,Takagi—Sugeno模糊模型的可辨识性条件。     

Identifiability of Dynamic Systems Represented by Bond Graphs

In this paper, the identifiability of dynamical systems is presented from the perspective of the Bond Graph Methodology. Several classical approaches for identifiability are studied and their applicability to bond graphs is discussed. The Markov Parameter method was selected to determine local identifiability of linear systems and a methodical procedure to obtain Markov Parameters directly from the bond graph is presented which is based on its causal paths. This method can easily be implemented in on a computer and works for bond graphs with derivative causality elements and fields.     

Identifying Mixtures of Mixtures Using Bayesian Estimation

The use of a finite mixture of normal distributions in model-based clustering allows us to capture non-Gaussian data clusters. However, identifying the clusters from the normal components is challenging and in general either achieved by imposing constraints on the model or by using post-processing procedures. Within the Bayesian framework, we propose a different approach based on sparse finite mixtures to achieve identifiability. We specify a hierarchical prior, where the hyperparameters are carefully selected such that they are reflective of the cluster structure aimed at. In addition, this prior allows us to estimate the model using standard MCMC sampling methods. In combination with a post-processing approach which resolves the label switching issue and results in an identified model, our approach allows us to simultaneously (1) determine the number of clusters, (2) flexibly approximate the cluster distributions in a semiparametric way using finite mixtures of normals and (3) identify cluster-specific parameters and classify observations. The proposed approach is illustrated in two simulation studies and on benchmark datasets. Supplementary materials for this article are available online.