arXiv subjects

Takahiro Onizuka

Publications and source records attributed to Takahiro Onizuka.

9 recordsLinked to original sources

arXiv2026

Learning rate selection via weighted Fisher divergence

The general Bayesian approach provides a flexible framework by introducing a loss-based likelihood with a learning rate controlling the relative weight of the likelihood and prior. This flexibility creates an important calibration problem under model misspecification, where the conventional Bayesian information identity fails and uncalibrated Gibbs posteriors may not provide reliable uncertainty quantification. We propose a method for selecting the learning rate by minimizing a weighted Fisher divergence between the asymptotic general posterior and a normal distribution with sandwich-type covariance, yielding a closed-form calibrated learning rate. The proposed framework includes Fisher information matching as a special case and, for an important choice of the weight matrix, yields a learning rate no larger than the Fisher information matching rate. This leads to a more dispersed posterior and can reduce the risk of undercoverage. The framework also includes a learning rate based on Kullback--Leibler divergence as a special case. Numerical examples show that the proposed method tends to mitigate undercoverage under model misspecification, while real-data analyses illustrate its practical applicability.

stat.ME↗

arXiv2026

Bayesian spatiotemporal conditional autoregressive model for local temporal variations

Spatiotemporal areal data are commonly observed in various fields such including epidemiology, social science, economics and so on. To capture both spatial trends and temporal trends, spatiotemporal modeling is often employed, and the conditional autoregressive (CAR) model is one of the most widely used approaches for modeling areal data. This paper proposes a new framework for estimating spatiotemporal trends based on the CAR model. The proposed method provides locally adaptive temporal smoothing while yielding interpretable temporal trends by effectively utilizing information from both spatially neighboring areas and temporally adjacent time points. We also develop a Gibbs sampling algorithm and demonstrate the ability of the proposed method to adapt to to local temporal changes through numerical examples.

stat.ME↗

arXiv2026

Global-local shrinkage priors for modeling random effects in multivariate spatial small area estimation

Small area estimation (SAE) plays a central role in survey statistics and epidemiology, providing reliable estimates for domains with limited sample sizes. The multivariate Fay-Herriot model has been extensively used for this purpose, because it enhances estimation accuracy by borrowing strength across multiple correlated variables. In this paper, we develop a Bayesian extension of the multivariate Fay-Herriot model that enables flexible, component-specific shrinkage of the random effects. The proposed approach employs global-local priors formulated through a sandwich mixture representation, allowing adaptive regularization of each element of the random-effect vectors. This construction yields greater robustness and prevents excessive shrinkage in areas exhibiting strong underlying signals. In addition, we incorporate spatial dependence into the model to account for geographical correlation across small areas. The resulting spatial multivariate framework simultaneously exploits cross-variable relationships and spatial structure, yielding improved estimation efficiency. The utility of the proposed method is demonstrated through simulation studies and an empirical application to real survey data.

stat.ME↗

arXiv2025

Robust Bayesian Inference for Censored Survival Models

This paper proposes a robust Bayesian accelerated failure time model for censored survival data. We develop a new family of life-time distributions using a scale mixture of the generalized gamma distributions, where we propose a novel super heavy-tailed distribution as a mixing density. We theoretically show that, under some conditions, the proposed method satisfies the full posterior robustness, which guarantees robustness of point estimation as well as uncertainty quantification. For posterior computation, we employ an integral expression of the proposed heavy-tailed distribution to develop an efficient posterior computation algorithm based on the Markov chain Monte Carlo. The performance of the proposed method is illustrated through numerical experiments and real data example.

stat.ME↗

arXiv2025

Robust Bayesian graphical modeling using $γ$-divergence

Gaussian graphical model is one of the powerful tools to analyze conditional independence between two variables for multivariate Gaussian-distributed observations. When the dimension of data is moderate or high, penalized likelihood methods such as the graphical lasso are useful to detect significant conditional independence structures. However, the estimates are affected by outliers due to the Gaussian assumption. This paper proposes a novel robust posterior distribution for inference of Gaussian graphical models using the $γ$-divergence which is one of the robust divergences. In particular, we focus on the Bayesian graphical lasso by assuming the Laplace-type prior for elements of the inverse covariance matrix. The proposed posterior distribution matches its maximum a posteriori estimate with the minimum $γ$-divergence estimate provided by the frequentist penalized method. We show that the proposed method satisfies the posterior robustness which is a kind of measure of robustness in Bayesian analysis. The property means that the information of outliers is automatically ignored in the posterior distribution as long as the outliers are extremely large. A sufficient condition for the posterior propriety of the proposed posterior distribution is also derived. Furthermore, an efficient posterior computation algorithm via the weighted Bayesian bootstrap method is proposed. The performance of the proposed method is illustrated through simulation studies and real data analysis.

stat.ME↗

arXiv2023

Bayesian Boundary Trend Filtering

Estimating boundary curves has many applications such as economics, climate science, and medicine. Bayesian trend filtering has been developed as one of locally adaptive smoothing methods to estimate the non-stationary trend of data. This paper develops a Bayesian trend filtering for estimating the boundary trend. To this end, the truncated multivariate normal working likelihood and global-local shrinkage priors based on the scale mixtures of normal distribution are introduced. In particular, well-known horseshoe prior for difference leads to locally adaptive shrinkage estimation for boundary trend. However, the full conditional distributions of the Gibbs sampler involve high-dimensional truncated multivariate normal distribution. To overcome the difficulty of sampling, an approximation of truncated multivariate normal distribution is employed. Using the approximation, the proposed models lead to an efficient Gibbs sampling algorithm via the Pólya-Gamma data augmentation. The proposed method is also extended by considering a nearly isotonic constraint. The performance of the proposed method is illustrated through some numerical experiments and real data examples.

stat.ME↗

arXiv2023

Locally Adaptive Spatial Quantile Smoothing: Application to Monitoring Crime Density in Tokyo

Spatial trend estimation under potential heterogeneity is an important problem to extract spatial characteristics and hazards such as criminal activity. By focusing on quantiles, which provide substantial information on distributions compared with commonly used summary statistics such as means, it is often useful to estimate not only the average trend but also the high (low) risk trend additionally. In this paper, we propose a Bayesian quantile trend filtering method to estimate the non-stationary trend of quantiles on graphs and apply it to crime data in Tokyo between 2013 and 2017. By modeling multiple observation cases, we can estimate the potential heterogeneity of spatial crime trends over multiple years in the application. To induce locally adaptive Bayesian inference on trends, we introduce general shrinkage priors for graph differences. Introducing so-called shadow priors with multivariate distribution for local scale parameters and mixture representation of the asymmetric Laplace distribution, we provide a simple Gibbs sampling algorithm to generate posterior samples. The numerical performance of the proposed method is demonstrated through simulation studies.

stat.ME↗

arXiv2023

Fast and Locally Adaptive Bayesian Quantile Smoothing using Calibrated Variational Approximations

Quantiles are useful characteristics of random variables that can provide substantial information on distributions compared with commonly used summary statistics such as means. In this paper, we propose a Bayesian quantile trend filtering method to estimate non-stationary trend of quantiles. We introduce general shrinkage priors to induce locally adaptive Bayesian inference on trends and mixture representation of the asymmetric Laplace likelihood. To quickly compute the posterior distribution, we develop calibrated mean-field variational approximations to guarantee that the frequentist coverage of credible intervals obtained from the approximated posterior is a specified nominal level. Simulation and empirical studies show that the proposed algorithm is computationally much more efficient than the Gibbs sampler and tends to provide stable inference results, especially for high/low quantiles.

stat.ME↗

arXiv2022

Sparse Bayesian inference on gamma-distributed observations using shape-scale inverse-gamma mixtures

In various applications, we deal with high-dimensional positive-valued data that often exhibits sparsity. This paper develops a new class of continuous global-local shrinkage priors tailored to analyzing gamma-distributed observations where most of the underlying means are concentrated around a certain value. Unlike existing shrinkage priors, our new prior is a shape-scale mixture of inverse-gamma distributions, which has a desirable interpretation of the form of posterior mean and admits flexible shrinkage. We show that the proposed prior has two desirable theoretical properties; Kullback-Leibler super-efficiency under sparsity and robust shrinkage rules for large observations. We propose an efficient sampling algorithm for posterior inference. The performance of the proposed method is illustrated through simulation and two real data examples, the average length of hospital stay for COVID-19 in South Korea and adaptive variance estimation of gene expression data.

stat.ME↗