Subjects -> STATISTICS (Total: 130 journals)
 The end of the list has been reached or no journals were found for your choice.
Similar Journals
 Statistics and ComputingJournal Prestige (SJR): 2.545 Citation Impact (citeScore): 2Number of Followers: 14      Hybrid journal (It can contain Open Access articles) ISSN (Print) 1573-1375 - ISSN (Online) 0960-3174 Published by Springer-Verlag  [2469 journals]
• Geometry-informed irreversible perturbations for accelerated convergence
of Langevin dynamics

Abstract: Abstract We introduce a novel geometry-informed irreversible perturbation that accelerates convergence of the Langevin algorithm for Bayesian computation. It is well documented that there exist perturbations to the Langevin dynamics that preserve its invariant measure while accelerating its convergence. Irreversible perturbations and reversible perturbations (such as Riemannian manifold Langevin dynamics (RMLD)) have separately been shown to improve the performance of Langevin samplers. We consider these two perturbations simultaneously by presenting a novel form of irreversible perturbation for RMLD that is informed by the underlying geometry. Through numerical examples, we show that this new irreversible perturbation can improve estimation performance over irreversible perturbations that do not take the geometry into account. Moreover we demonstrate that irreversible perturbations generally can be implemented in conjunction with the stochastic gradient version of the Langevin algorithm. Lastly, while continuous-time irreversible perturbations cannot impair the performance of a Langevin estimator, the situation can sometimes be more complicated when discretization is considered. To this end, we describe a discrete-time example in which irreversibility increases both the bias and variance of the resulting estimator.
PubDate: 2022-09-19

• Mixture of multivariate Gaussian processes for classification of
irregularly sampled satellite image time-series

Abstract: Abstract The classification of irregularly sampled Satellite image time-series (SITS) is investigated in this paper. A multivariate Gaussian process mixture model is proposed to address the irregular sampling, the multivariate nature of the time-series and the scalability to large data-sets. The spectral and temporal correlation is handled using a Kronecker structure on the covariance operator of the Gaussian process. The multivariate Gaussian process mixture model allows both for the classification of time-series and the imputation of missing values. Experimental results on simulated and real SITS data illustrate the importance of taking into account the spectral correlation to ensure a good behavior in terms of classification accuracy and reconstruction errors.
PubDate: 2022-09-19

• Sequential sampling of junction trees for decomposable graphs

Abstract: Abstract The junction-tree representation provides an attractive structural property for organising a decomposable graph. In this study, we present two novel stochastic algorithms, referred to as the junction-tree expander and junction-tree collapser, for sequential sampling of junction trees for decomposable graphs. We show that recursive application of the junction-tree expander, which expands incrementally the underlying graph with one vertex at a time, has full support on the space of junction trees for any given number of underlying vertices. On the other hand, the junction-tree collapser provides a complementary operation for removing vertices in the underlying decomposable graph of a junction tree, while maintaining the junction tree property. A direct application of the proposed algorithms is demonstrated in the setting of sequential Monte Carlo methods, designed for sampling from distributions on spaces of decomposable graphs. Numerical studies illustrate the utility of the proposed algorithms for combinatorial computations on decomposable graphs and junction trees. All the methods proposed in the paper are implemented in the Python library trilearn.
PubDate: 2022-09-19

• Achieving fairness with a simple ridge penalty

Abstract: Abstract In this paper, we present a general framework for estimating regression models subject to a user-defined level of fairness. We enforce fairness as a model selection step in which we choose the value of a ridge penalty to control the effect of sensitive attributes. We then estimate the parameters of the model conditional on the chosen penalty value. Our proposal is mathematically simple, with a solution that is partly in closed form and produces estimates of the regression coefficients that are intuitive to interpret as a function of the level of fairness. Furthermore, it is easily extended to generalised linear models, kernelised regression models and other penalties, and it can accommodate multiple definitions of fairness. We compare our approach with the regression model from Komiyama et al. (in: Proceedings of machine learning research. 35th international conference on machine learning (ICML), vol 80, pp 2737–2746, 2018), which implements a provably optimal linear regression model and with the fair models from Zafar et al. (J Mach Learn Res 20:1–42, 2019). We evaluate these approaches empirically on six different data sets, and we find that our proposal provides better goodness of fit and better predictive accuracy for the same level of fairness. In addition, we highlight a source of bias in the original experimental evaluation in Komiyama et al. (in: Proceedings of machine learning research. 35th international conference on machine learning (ICML), vol 80, pp 2737–2746, 2018).
PubDate: 2022-09-18

• Default risk prediction and feature extraction using a penalized deep
neural network

Abstract: Abstract Online peer-to-peer lending platforms provide loans directly from lenders to borrowers without passing through traditional financial institutions. For lenders on these platforms to avoid loss, it is crucial that they accurately assess default risk so that they can make appropriate decisions. In this study, we develop a penalized deep learning model to predict default risk based on survival data. As opposed to simply predicting whether default will occur, we focus on predicting the probability of default over time. Moreover, by adding an additional one-to-one layer in the neural network, we achieve feature selection and estimation simultaneously by incorporating an $$L_1$$ -penalty into the objective function. The minibatch gradient descent algorithm makes it possible to handle massive data. An analysis of a real-world loan data and simulations demonstrate the model’s competitive practical performance, which suggests favorable potential applications in peer-to-peer lending platforms.
PubDate: 2022-09-15

• Quantile regression feature selection and estimation with grouped
variables using Huber approximation

Abstract: Abstract This paper considers model selection and estimation for quantile regression with a known group structure in the predictors. For the median case the model is estimated by minimizing a penalized objective function with Huber loss and the group lasso penalty. While, for other quantiles an M-quantile approach, an asymmetric version of Huber loss, is used which approximates the standard quantile loss function. This approximation allows for efficient implementation of algorithms which rely on a differentiable loss function. Rates of convergence are provided which demonstrate the potential advantages of using the group penalty and that bias from the Huber-type approximation vanishes asymptotically. An efficient algorithm is discussed, which provides fast and accurate estimation for quantile regression models. Simulation and empirical results are provided to demonstrate the effectiveness of the proposed algorithm and support the theoretical results.
PubDate: 2022-09-11

• Kryging: geostatistical analysis of large-scale datasets using Krylov
subspace methods

Abstract: Abstract Analyzing massive spatial datasets using a Gaussian process model poses computational challenges. This is a problem prevailing heavily in applications such as environmental modeling, ecology, forestry and environmental health. We present a novel approximate inference methodology that uses profile likelihood and Krylov subspace methods to estimate the spatial covariance parameters and makes spatial predictions with uncertainty quantification for point-referenced spatial data. “Kryging” combines Kriging and Krylov subspace methods and applies for both observations on regular grid and irregularly spaced observations, and for any Gaussian process with a stationary isotropic (and certain geometrically anisotropic) covariance function, including the popular Matérn  covariance family. We make use of the block Toeplitz structure with Toeplitz blocks of the covariance matrix and use fast Fourier transform methods to bypass the computational and memory bottlenecks of approximating log-determinant and matrix-vector products. We perform extensive simulation studies to show the effectiveness of our model by varying sample sizes, spatial parameter values and sampling designs. A real data application is also performed on a dataset consisting of land surface temperature readings taken by the MODIS satellite. Compared to existing methods, the proposed method performs satisfactorily with much less computation time and better scalability.
PubDate: 2022-09-08

• Improving bridge estimators via f-GAN

Abstract: Abstract Bridge sampling is a powerful Monte Carlo method for estimating ratios of normalizing constants. Various methods have been introduced to improve its efficiency. These methods aim to increase the overlap between the densities by applying appropriate transformations to them without changing their normalizing constants. In this paper, we first give a new estimator of the asymptotic relative mean square error (RMSE) of the optimal Bridge estimator by equivalently estimating an f-divergence between the two densities. We then utilize this framework and propose f-GAN-Bridge estimator (f-GB) based on a bijective transformation that maps one density to the other and minimizes the asymptotic RMSE of the optimal Bridge estimator with respect to the densities. This transformation is chosen by minimizing a specific f-divergence between the densities. We show f-GB is optimal in the sense that within any given set of candidate transformations, the f-GB estimator can asymptotically achieve an RMSE lower than or equal to that achieved by Bridge estimators based on any other transformed densities. Numerical experiments show that f-GB outperforms existing methods in simulated and real-world examples. In addition, we discuss how Bridge estimators naturally arise from the problem of f-divergence estimation.
PubDate: 2022-09-03

• A non-stationary model for spatially dependent circular response data
based on wrapped Gaussian processes

Abstract: Abstract Circular data can be found across many areas of science, for instance meteorology (e.g., wind directions), ecology (e.g., animal movement directions), or medicine (e.g., seasonality in disease onset). The special nature of these data means that conventional methods for non-periodic data are no longer valid. In this paper, we consider wrapped Gaussian processes and introduce a spatial model for circular data that allow for non-stationarity in the mean and the covariance structure of Gaussian random fields. We use the empirical equivalence between Gaussian random fields and Gaussian Markov random fields which allows us to considerably reduce computational complexity by exploiting the sparseness of the precision matrix of the associated Gaussian Markov random field. Furthermore, we develop tunable priors, inspired by the penalized complexity prior framework, that shrink the model toward a less flexible base model with stationary mean and covariance function. Posterior estimation is done via Markov chain Monte Carlo simulation. The performance of the model is evaluated in a simulation study. Finally, the model is applied to analyzing wind directions in Germany.
PubDate: 2022-09-03

• Convergence rate bounds for iterative random functions using one-shot
coupling

Abstract: Abstract One-shot coupling is a method of bounding the convergence rate between two copies of a Markov chain in total variation distance, which was first introduced in Roberts and Rosenthal (Process Appl 99:195–208, 2002) and generalized in Madras and Sezer (Bernoulli 16:882–908, 2010). The method is divided into two parts: the contraction phase, when the chains converge in expected distance and the coalescing phase, which occurs at the last iteration, when there is an attempt to couple. One-shot coupling does not require the use of any exogenous variables like a drift function or a minorization constant. In this paper, we summarize the one-shot coupling method into the One-Shot Coupling Theorem. We then apply the theorem to two families of Markov chains: the random functional autoregressive process and the autoregressive conditional heteroscedastic process. We provide multiple examples of how the theorem can be used on various models including ones in high dimensions. These examples illustrate how the theorem’s conditions can be verified in a straightforward way. The one-shot coupling method appears to generate tight geometric convergence rate bounds.
PubDate: 2022-09-02

• Variational inference and sparsity in high-dimensional deep Gaussian
mixture models

Abstract: Abstract Gaussian mixture models are a popular tool for model-based clustering, and mixtures of factor analyzers are Gaussian mixture models having parsimonious factor covariance structure for mixture components. There are several recent extensions of mixture of factor analyzers to deep mixtures, where the Gaussian model for the latent factors is replaced by a mixture of factor analyzers. This construction can be iterated to obtain a model with many layers. These deep models are challenging to fit, and we consider Bayesian inference using sparsity priors to further regularize the estimation. A scalable natural gradient variational inference algorithm is developed for fitting the model, and we suggest computationally efficient approaches to the architecture choice using overfitted mixtures where unnecessary components drop out in the estimation. In a number of simulated and two real examples, we demonstrate the versatility of our approach for high-dimensional problems, and demonstrate that the use of sparsity inducing priors can be helpful for obtaining improved clustering results.
PubDate: 2022-09-01

• A Joint estimation approach to sparse additive ordinary differential
equations

Abstract: Abstract Ordinary differential equations (ODEs) are widely used to characterize the dynamics of complex systems in real applications. In this article, we propose a novel joint estimation approach for generalized sparse additive ODEs where observations are allowed to be non-Gaussian. The new method is unified with existing collocation methods by considering the likelihood, ODE fidelity and sparse regularization simultaneously. We design a block coordinate descent algorithm for optimizing the non-convex and non-differentiable objective function. The global convergence of the algorithm is established. The simulation study and two applications demonstrate the superior performance of the proposed method in estimation and improved performance of identifying the sparse structure.
PubDate: 2022-08-23

• A joint latent factor analyzer and functional subspace model for
clustering multivariate functional data

Abstract: Abstract We introduce a model-based approach for clustering multivariate functional data observations. We utilize theoretical results regarding a surrogate density on the truncated Karhunen–Loeve expansions along with a direct sum specification of the functional space to define a matrix normal distribution on functional principal components. This formulation allows for individual parsimonious modelling of the function space and coefficient space of the univariate components of the multivariate functional observations in the form a subspace projection and latent factor analyzers, respectively. The approach facilitates interpretation at both the full multivariate level and the component level, which is of specific interest when the component functions have clear meaning. We derive an AECM algorithm for fitting the model, and discuss appropriate initialization strategies, convergence and model selection criteria. We demonstrate the model’s applicability through simulation and two data analyses on observations that have many functional components.
PubDate: 2022-08-20

• Computing marginal likelihoods via the Fourier integral theorem and
pointwise estimation of posterior densities

Abstract: Abstract In this paper, we present a novel approach to the estimation of a density function at a specific chosen point. With this approach, we can estimate a normalizing constant, or equivalently compute a marginal likelihood, by focusing on estimating a posterior density function at a point. Relying on the Fourier integral theorem, the proposed method is capable of producing quick and accurate estimates of the marginal likelihood, regardless of how samples are obtained from the posterior; that is, it uses the posterior output generated by a Markov chain Monte Carlo sampler to estimate the marginal likelihood directly, with no modification to the form of the estimator on the basis of the type of sampler used. Thus, even for models with complicated specifications, such as those involving challenging hierarchical structures, or for Markov chains obtained from a black-box MCMC algorithm, the method provides a straightforward means of quickly and accurately estimating the marginal likelihood. In addition to developing theory to support the favorable behavior of the estimator, we also present a number of illustrative examples.
PubDate: 2022-08-16

• Statistic selection and MCMC for differentially private Bayesian
estimation

Abstract: Abstract This paper concerns differentially private Bayesian estimation of the parameters of a population distribution, when a noisy statistic of a sample from that population is shared to provide differential privacy. This work mainly addresses two problems. (1) What statistics of the sample should be shared privately' For this question, we promote using the Fisher information. We find out that the statistic that is most informative in a non-privacy setting may not be the optimal choice under the privacy restrictions. We provide several examples to support that point. We consider several types of data sharing settings and propose several Monte Carlo-based numerical estimation methods for calculating the Fisher information for those settings. The second question concerns inference: (2) Based on the shared statistics, how could we perform effective Bayesian inference' We propose several Markov chain Monte Carlo (MCMC) algorithms for sampling from the posterior distribution of the parameter given the noisy statistic. The proposed MCMC algorithms can be preferred over one another depending on the problem. For example, when the shared statistic is additive and added Gaussian noise, a simple Metropolis-Hasting algorithm that utilises the central limit theorem is a decent choice. We propose more advanced MCMC algorithms for several other cases of practical relevance. Our numerical examples involve comparing several candidate statistics to be shared privately. For each statistic, we perform Bayesian estimation based on the posterior distribution conditional on the privatised version of that statistic. We demonstrate that the relative performance of a statistic, in terms of the mean squared error of the Bayesian estimator based on the corresponding privatised statistic, is adequately predicted by the Fisher information of the privatised statistic.
PubDate: 2022-08-16

• A 4D-Var method with flow-dependent background covariances for the
shallow-water equations

Abstract: Abstract The 4D-Var method for filtering partially observed nonlinear chaotic dynamical systems consists of finding the maximum a-posteriori (MAP) estimator of the initial condition of the system given observations over a time window, and propagating it forward to the current time via the model dynamics. This method forms the basis of most currently operational weather forecasting systems. In practice the optimisation becomes infeasible if the time window is too long due to the non-convexity of the cost function, the effect of model errors, and the limited precision of the ODE solvers. Hence the window has to be kept sufficiently short, and the observations in the previous windows can be taken into account via a Gaussian background (prior) distribution. The choice of the background covariance matrix is an important question that has received much attention in the literature. In this paper, we define the background covariances in a principled manner, based on observations in the previous b assimilation windows, for a parameter $$b\ge 1$$ . The method is at most b times more computationally expensive than using fixed background covariances, requires little tuning, and greatly improves the accuracy of 4D-Var. As a concrete example, we focus on the shallow-water equations. The proposed method is compared against state-of-the-art approaches in data assimilation and is shown to perform favourably on simulated data. We also illustrate our approach on data from the recent tsunami of 2011 in Fukushima, Japan.
PubDate: 2022-08-11

• On automatic bias reduction for extreme expectile estimation

Abstract: Abstract Expectiles induce a law-invariant risk measure that has recently gained popularity in actuarial and financial risk management applications. Unlike quantiles or the quantile-based Expected Shortfall, the expectile risk measure is coherent and elicitable. The estimation of extreme expectiles in the heavy-tailed framework, which is reasonable for extreme financial or actuarial risk management, is not without difficulties; currently available estimators of extreme expectiles are typically biased and hence may show poor finite-sample performance even in fairly large samples. We focus here on the construction of bias-reduced extreme expectile estimators for heavy-tailed distributions. The rationale for our construction hinges on a careful investigation of the asymptotic proportionality relationship between extreme expectiles and their quantile counterparts, as well as of the extrapolation formula motivated by the heavy-tailed context. We accurately quantify and estimate the bias incurred by the use of these relationships when constructing extreme expectile estimators. This motivates the introduction of classes of bias-reduced estimators whose asymptotic properties are rigorously shown, and whose finite-sample properties are assessed on a simulation study and three samples of real data from economics, insurance and finance.
PubDate: 2022-08-09

• The computational asymptotics of Gaussian variational inference and the
Laplace approximation

Abstract: Abstract Gaussian variational inference and the Laplace approximation are popular alternatives to Markov chain Monte Carlo that formulate Bayesian posterior inference as an optimization problem, enabling the use of simple and scalable stochastic optimization algorithms. However, a key limitation of both methods is that the solution to the optimization problem is typically not tractable to compute; even in simple settings, the problem is nonconvex. Thus, recently developed statistical guarantees—which all involve the (data) asymptotic properties of the global optimum—are not reliably obtained in practice. In this work, we provide two major contributions: a theoretical analysis of the asymptotic convexity properties of variational inference with a Gaussian family and the maximum a posteriori (MAP) problem required by the Laplace approximation, and two algorithms—consistent Laplace approximation (CLA) and consistent stochastic variational inference (CSVI)—that exploit these properties to find the optimal approximation in the asymptotic regime. Both CLA and CSVI involve a tractable initialization procedure that finds the local basin of the optimum, and CSVI further includes a scaled gradient descent algorithm that provably stays locally confined to that basin. Experiments on nonconvex synthetic and real-data examples show that compared with standard variational and Laplace approximations, both CSVI and CLA improve the likelihood of obtaining the global optimum of their respective optimization problems.
PubDate: 2022-08-09

• Rate-optimal refinement strategies for local approximation MCMC

Abstract: Abstract Many Bayesian inference problems involve target distributions whose density functions are computationally expensive to evaluate. Replacing the target density with a local approximation based on a small number of carefully chosen density evaluations can significantly reduce the computational expense of Markov chain Monte Carlo (MCMC) sampling. Moreover, continual refinement of the local approximation can guarantee asymptotically exact sampling. We devise a new strategy for balancing the decay rate of the bias due to the approximation with that of the MCMC variance. We prove that the error of the resulting local approximation MCMC (LA-MCMC) algorithm decays at roughly the expected $$1/\sqrt{T}$$ rate, and we demonstrate this rate numerically. We also introduce an algorithmic parameter that guarantees convergence given very weak tail bounds, significantly strengthening previous convergence results. Finally, we apply LA-MCMC to a computationally intensive Bayesian inverse problem arising in groundwater hydrology.
PubDate: 2022-08-09

• Quantile hidden semi-Markov models for multivariate time series

Abstract: Abstract This paper develops a quantile hidden semi-Markov regression to jointly estimate multiple quantiles for the analysis of multivariate time series. The approach is based upon the Multivariate Asymmetric Laplace (MAL) distribution, which allows to model the quantiles of all univariate conditional distributions of a multivariate response simultaneously, incorporating the correlation structure among the outcomes. Unobserved serial heterogeneity across observations is modeled by introducing regime-dependent parameters that evolve according to a latent finite-state semi-Markov chain. Exploiting the hierarchical representation of the MAL, inference is carried out using an efficient Expectation-Maximization algorithm based on closed form updates for all model parameters, without parametric assumptions about the states’ sojourn distributions. The validity of the proposed methodology is analyzed both by a simulation study and through the empirical analysis of air pollutant concentrations in a small Italian city.
PubDate: 2022-08-09

JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762