arXiv subjects

Daniele Durante

Publications and source records attributed to Daniele Durante.

At least 19 recordsLinked to original sources

arXiv2026

Bayesian nonparametric inference for modal missing species and features

Species and feature sampling problems arise naturally whenever each observed unit is associated with one or more labels from a countable alphabet, and inference focuses on the unobserved portion of the distribution over such an alphabet. Within this framework, recent contributions have shifted attention from inference on the total probability mass over unseen labels to distribution-free confidence intervals for the largest unobserved label probability (i.e., the modal missing probability), thereby providing more refined information on whether the missing mass is concentrated on a few high-prevalence unseen labels or distributed across many negligible ones. Besides lacking a unified framework for species and features, these approaches employ a worst-case perspective that causes substantial information loss and produces overly-conservative intervals. We address these limitations through a unified model-based framework for inference on modal missing probabilities in both species and feature settings, which leverages a flexible Bayesian nonparametric formulation to localize uncertainty around models compatible with the observed data. This leads to sharper closed-form credible intervals that effectively exploit prior information and observed data, while preserving the theoretical frequentist properties and robustness of distribution-free intervals. Simulation studies confirm these improvements, while an organized crime application illustrates how our contribution has the potential to reshape law-enforcement decision-making in investigations.

stat.ME↗

arXiv2026

Phylogenetic latent space models for network data

Latent space models for network data characterize each node through a vector of latent features whose pairwise similarities define the edge probabilities among the pairs of nodes. Although this formulation has led to successful implementations, the overarching focus has been on directly inferring node embeddings through the latent features, rather than learning the generative process underlying these embeddings. This focus prevents borrowing information across the node features and limits the ability to infer higher-level architectures governing network formation. For example, routinely-studied networks often exhibit multiscale structures informing on nested modular hierarchies among nodes, which could be learned via tree-based representations of dependencies among the latent features. We pursue this direction by bridging latent variable representations of network data with concepts from phylogenetic inference to design a novel latent space model that explicitly characterizes the generative process of the node feature vectors through a branching Brownian motion, with branching structure parametrized by a tree. This tree constitutes the main object of interest and is learned under a Bayesian perspective leveraging priors inherited from phylogenetic literature to infer tree-based modular hierarchies across nodes, which explain heterogeneous multiscale patterns in the network. Identifiability results are derived along with posterior consistency theory. The inference potentials of our model are illustrated in simulations and two real-data applications from criminology and neuroscience, where our formulation learns core structures hidden to state-of-the-art alternatives.

stat.ME↗

arXiv2026

Low-rank bilinear autoregressive models for three-way criminal activity tensors

Criminal activity data are typically available via a three-way tensor encoding the reported frequencies of different crime categories across time and space. The challenges that arise in the design of interpretable, yet realistic, model-based representations of the complex dependencies within and across these three dimensions have led to an increasing adoption of black-box predictive strategies. While this perspective has proved successful in producing accurate forecasts guiding targeted interventions, the lack of interpretable model-based characterizations of the dependence structures underlying criminal activity tensors prevents from inferring the cascading effects of these interventions across the different dimensions. We address this gap through the design of a low-rank bilinear autoregressive model which achieves comparable predictive performance to black-box strategies, while allowing interpretable inference on the dependence structures of reported criminal activities across crime categories, time and space. This representation incorporates the time dimension via an autoregressive construction that accounts for spatial effects and dependencies among crime categories through a separable low-rank bilinear formulation. When applied to Chicago police reports, the proposed model showcases remarkable predictive performance and also reveals interpretable dependence structures unveiling fundamental crime dynamics. These results facilitate the design of more refined intervention policies informed by the cascading effects of the policy itself.

stat.AP↗

arXiv2026

Skew-symmetric approximations of posterior distributions

Popular deterministic approximations of posterior distributions from, e.g. the Laplace method, variational Bayes and expectation-propagation, generally rely on symmetric approximating families, often taken to be Gaussian. This choice facilitates optimization and inference, but typically affects the quality of the overall approximation. In fact, even in basic parametric models, the posterior distribution often displays asymmetries that yield bias and a reduced accuracy when considering symmetric approximations. Recent research has moved towards more flexible approximating families which incorporate skewness. However, current solutions are often model specific, lack a general supporting theory, increase the computational complexity of the optimization problem, and do not provide a broadly applicable solution to incorporate skewness in any symmetric approximation. This article addresses such a gap by introducing a general and provably optimal strategy to perturb any off-the-shelf symmetric approximation of a generic posterior distribution. This novel perturbation scheme is derived without additional optimization steps, and yields a similarly tractable approximation within the class of skew-symmetric densities that provably enhances the finite sample accuracy of the original symmetric counterpart. Furthermore, under suitable assumptions, it improves the convergence rate to the exact posterior by at least a $\sqrt{n}$ factor, in asymptotic regimes. These advancements are illustrated in numerical studies focusing on skewed perturbations of state-of-the-art Gaussian approximations.

stat.ME↗

arXiv2025

Optimal and computationally tractable lower bounds for logistic log-likelihoods

The logit transform is arguably the most widely-employed link function beyond linear settings. This transformation routinely appears in regression models for binary data and provides a central building-block in popular methods for both classification and regression. Its widespread use, combined with the lack of analytical solutions for the optimization of objective functions involving the logit transform, still motivates active research in computational statistics. Among the directions explored, a central one has focused on the design of tangent lower bounds for logistic log-likelihoods that can be tractably optimized, while providing a tight approximation of these log-likelihoods. This has led to the development of effective minorize-maximize (MM) algorithms for point estimation, and variational schemes for approximate Bayesian inference under several logit models. However, the overarching focus has been on tangent quadratic minorizers. In fact, it is still unclear whether tangent lower bounds sharper than quadratic ones can be derived without undermining the tractability of the resulting minorizer. This article addresses such a question through the design and study of a novel piece-wise quadratic lower bound that uniformly improves any tangent quadratic minorizer, including the sharpest ones, while admitting a direct interpretation in terms of the classical generalized lasso problem. As illustrated in realistic empirical studies, such a sharper bound not only improves the speed of convergence of common MM schemes for penalized maximum likelihood estimation, but also yields tractable variational Bayes (VB) approximations with higher accuracy relative to those obtained under popular quadratic bounds employed in VB.

stat.ML↗

arXiv2025

Dependent stochastic block models for age-indexed sequences of directed causes-of-death networks

Death events commonly arise from complex interactions among interrelated causes, formally classified in reporting practices as underlying and contributing. Leveraging information from death certificates, these interactions can be naturally represented through a sequence of directed networks encoding co-occurrence strengths between pairs of underlying and contributing causes across ages. Although this perspective opens the avenues to learn informative age-specific block interactions among endogenous groups of underlying and contributing causes displaying similar co-occurrence patterns, there has been limited research along this direction in mortality modeling. This is mainly due to the lack of suitable stochastic block models for age-indexed sequences of directed networks. We cover this gap through a novel Bayesian formulation which crucially learns two separate group structures for underlying and contributing causes, while allowing both structures to change smoothly across ages via dependent random partition priors. As illustrated in simulations, this formulation outperforms state-of-the-art solutions that could be adapted to our motivating application. Moreover, when applied to USA mortality data, it unveils structures in the composition, evolution, and modular interactions among causes-of-death groups that were hidden to previous studies. Such findings could have relevant policy implications and contribute to an improved understanding of the recent "death of despair" phenomena in USA.

stat.AP↗

arXiv2025

Partially exchangeable stochastic block models for (node-colored) multilayer networks

Multilayer networks generalize single-layered connectivity data in several directions. These generalizations include, among others, settings where multiple types of edges are observed among the same set of nodes (edge-colored networks) or where a single notion of connectivity is measured between nodes belonging to different pre-specified layers (node-colored networks). While progress has been made in statistical modeling of edge-colored networks, principled approaches that flexibly account for both within and across layer block-connectivity structures while incorporating layer information through a rigorous probabilistic construction are still lacking for node-colored multilayer networks. We fill this gap by introducing a novel class of partially exchangeable stochastic block models specified in terms of a hierarchical random partition prior for the allocation of nodes to groups, whose number is learned by the model. This goal is achieved without jeopardizing probabilistic coherence, uncertainty quantification and derivation of closed-form predictive within- and across-layer co-clustering probabilities. Our approach facilitates prior elicitation, the understanding of theoretical properties and the development of yet-unexplored predictive strategies for both the connections and the allocations of future incoming nodes. Posterior inference proceeds via a tractable collapsed Gibbs sampler, while performance is illustrated in simulations and in a real-world criminal network application. The notable gains achieved over competitors clarify the importance of developing general stochastic block models based on suitable node-exchangeability structures coherent with the type of multilayer network being analyzed.

stat.ME↗

arXiv2025

Bayesian local clustering of age-period mortality surfaces across multiple countries

Although traditional literature on mortality modeling has focused on single countries in isolation, recent contributions have progressively moved toward joint models for multiple countries. Besides favoring borrowing of information to improve age-period forecasts, this perspective has also potentials to infer local similarities among countries' mortality patterns in specific age classes and periods that could unveil unexplored demographic trends, while guiding the design of targeted policies. Advancements along this latter relevant direction are currently undermined by the lack of a multi-country model capable of incorporating the core structures of age-period mortality surfaces together with clustering patterns among countries that are not global, but rather vary locally across different combinations of ages and periods. We cover this gap by developing a novel Bayesian model for log-mortality rates that characterizes the age structure of mortality through a B-spline expansion whose country-specific dynamic coefficients encode both changes of this age structure across periods and also local clustering patterns among countries under a time-dependent random partition prior for these country-specific dynamic coefficients. While flexible, this formulation admits tractable posterior inference leveraging a suitably-designed Gibbs-sampler. The application to mortality data from 14 countries unveils local similarities highlighting both previously-recognized demographic phenomena and also yet-unexplored trends.

stat.AP↗

arXiv2025

Concentration of discrepancy-based approximate Bayesian computation via Rademacher complexity

There has been increasing interest on summary-free solutions for approximate Bayesian computation (ABC) which replace distances among summaries with discrepancies between the empirical distributions of the observed data and the synthetic samples generated under the proposed parameter values. The success of these strategies has motivated theoretical studies on the limiting properties of the induced posteriors. However, there is still the lack of a theoretical framework for summary-free ABC that (i) is unified, instead of discrepancy-specific, (ii) does not require to constrain the analysis to data generating processes and statistical models meeting specific regularity conditions, but rather facilitates the derivation of limiting properties that hold uniformly, and (iii) relies on verifiable assumptions that provide explicit concentration bounds clarifying which factors govern the limiting behavior of the ABC posterior. We address this gap via a novel theoretical framework that introduces the concept of Rademacher complexity in the analysis of the limiting properties for discrepancy-based ABC posteriors, including in non-i.i.d. and misspecified settings. This yields a unified theory that relies on constructive arguments and provides more informative asymptotic results and uniform concentration bounds, even in settings not covered by current studies. These advancements are obtained by relating the asymptotic properties of summary-free ABC posteriors to the behavior of the Rademacher complexity associated with the chosen discrepancy in the family of integral probability semimetrics (IPS). The IPS class extends summary-based distances, and includes the Wasserstein distance and maximum mean discrepancy, among others. As clarified in specialized theoretical analyses of popular IPS discrepancies and via illustrative simulations, this perspective improves the understanding of summary-free ABC.

stat.ME↗

arXiv2024

Zero-inflated stochastic block modeling of efficiency-security tradeoffs in weighted criminal networks

Criminal networks arise from the unique attempt to balance a need of establishing frequent ties among affiliates to facilitate the coordination of illegal activities, with the necessity to sparsify the overall connectivity architecture to hide from law enforcement. This efficiency-security tradeoff is also combined with the creation of groups of redundant criminals that exhibit similar connectivity patterns, thus guaranteeing resilient network architectures. State-of-the-art models for such data are not designed to infer these unique structures. In contrast to such solutions we develop a computationally-tractable Bayesian zero-inflated Poisson stochastic block model (ZIP-SBM), which identifies groups of redundant criminals with similar connectivity patterns, and infers both overt and covert block interactions within and across such groups. This is accomplished by modeling weighted ties (corresponding to counts of interactions among pairs of criminals) via zero-inflated Poisson distributions with block-specific parameters that quantify complex patterns in the excess of zero ties in each block (security) relative to the distribution of the observed weighted ties within that block (efficiency). The performance of ZIP-SBM is illustrated in simulations and in a study of summits co-attendances in a complex Mafia organization, where we unveil efficiency-security structures adopted by the criminal organization that were hidden to previous analyses.

stat.AP↗

arXiv2024

Conjugacy properties of multivariate unified skew-elliptical distributions

The broad class of multivariate unified skew-normal (SUN) distributions has been recently shown to possess important conjugacy properties. When used as priors for the coefficients vector in probit, tobit, and multinomial probit models, these distributions yield posteriors that still belong to the SUN family. Although this result has led to important advancements in Bayesian inference and computation, its applicability beyond likelihoods associated with fully-observed, discretized, or censored realizations from multivariate Gaussian models remains yet unexplored. This article covers such a gap by proving that the wider family of multivariate unified skew-elliptical (SUE) distributions, which extends SUNs to more general perturbations of elliptical densities, guarantees conjugacy for broader classes of models, beyond those relying on fully-observed, discretized or censored Gaussians. Such a result leverages the closure under linear combinations, conditioning and marginalization of SUE to prove that this family is conjugate to the likelihood induced by multivariate regression models for fully-observed, censored or dichotomized realizations from skew-elliptical distributions. This advancement enlarges the set of models that enable conjugate Bayesian inference to general formulations arising from elliptical and skew-elliptical families, including the multivariate Student's t and skew-t, among others.

stat.ME↗

arXiv2024

Skewed Bernstein-von Mises theorem and skew-modal approximations

Gaussian approximations are routinely employed in Bayesian statistics to ease inference when the target posterior is intractable. Although these approximations are asymptotically justified by Bernstein-von Mises type results, in practice the expected Gaussian behavior may poorly represent the shape of the posterior, thus affecting approximation accuracy. Motivated by these considerations, we derive an improved class of closed-form approximations of posterior distributions which arise from a new treatment of a third-order version of the Laplace method yielding approximations in a tractable family of skew-symmetric distributions. Under general assumptions which account for misspecified models and non-i.i.d. settings, this family of approximations is shown to have a total variation distance from the target posterior whose rate of convergence improves by at least one order of magnitude the one established by the classical Bernstein-von Mises theorem. Specializing this result to the case of regular parametric models shows that the same improvement in approximation accuracy can be also derived for polynomially bounded posterior functionals. Unlike other higher-order approximations, our results prove that it is possible to derive closed-form and valid densities which are expected to provide, in practice, a more accurate, yet similarly-tractable, alternative to Gaussian approximations of the target posterior, while inheriting its limiting frequentist properties. We strengthen such arguments by developing a practical skew-modal approximation for both joint and marginal posteriors that achieves the same theoretical guarantees of its theoretical counterpart by replacing the unknown model parameters with the corresponding MAP estimate. Empirical studies confirm that our theoretical results closely match the remarkable performance observed in practice, even in finite, possibly small, sample regimes.

math.ST↗

arXiv2024

Learning and forecasting of age-specific period mortality via B-spline processes with locally-adaptive dynamic coefficients

Although the analysis of human mortality has a well-established history, the attempt to accurately forecast future death-rate patterns for different age groups and time horizons still attracts active research. Such a predictive focus has motivated an increasing shift towards more flexible representations of age-specific period mortality trajectories at the cost of reduced interpretability. Although this perspective has led to successful predictive strategies, the inclusion of interpretable structures in modeling of human mortality can be, in fact, beneficial for improving forecasts. We pursue this direction via a novel B-spline process with locally-adaptive dynamic coefficients. Such a process outperforms state-of-the-art forecasting strategies by explicitly incorporating the core structures of period mortality within an interpretable formulation which enables inference on age-specific mortality trends and the corresponding rates of change across time. This is obtained by modeling the age-specific death counts via a Poisson log-normal model parameterized through a linear combination of B-spline bases with dynamic coefficients that characterize time changes in mortality rates via suitable stochastic differential equations. While flexible, the resulting formulation can be accurately approximated by a Gaussian state-space model that facilitates closed-form Kalman filtering, smoothing and forecasting, for both the trends of the spline coefficients and the corresponding first derivatives, which measure rates of change in mortality for different ages. As illustrated in applications to mortality data from different countries, our model outperforms state-of-the-art methods both in point forecasts and in calibration of predictive intervals. Moreover, it unveils substantial differences in mortality patterns across countries and ages, both in the past decades and during the COVID-19 pandemic.

stat.AP↗

arXiv2023

One EURO for Uranus: the Elliptical Uranian Relativity Orbiter mission

Recent years have seen increasing interest in sending a mission to Uranus, visited so far only by Voyager 2 in 1986. EURO (Elliptical Uranian Relativity Orbiter) is a preliminary mission concept investigating the possibility of dynamically measuring the planet's angular momentum by means of the Lense-Thirring effect affecting a putative Uranian orbiter. It is possible, at least in principle, to separate the relativistic precessions of the orbital inclination to the Celestial Equator and of the longitude of the ascending node of the spacecraft from its classical rates of the pericentre induced by the multipoles of the planet's gravity field by adopting an appropriate orbital configuration. For a wide and elliptical $2\,000\times 100\,000\,\mathrm{km}$ orbit, the gravitomagnetic signatures amount to tens of milliarcseconds per year, while, for a suitable choice of the initial conditions, the peak-to-peak amplitude of the range-rate shift can reach the level of $\simeq 1.5\times 10^{-3}$ millimetre per second in a single pericentre passage of a few hours. By lowering the apocentre height to $10\,000\,\mathrm{km}$, the Lense-Thirring precessions are enhanced to the level of hundreds of milliarcseconds per year. The uncertainties in the orientation of the planetary spin axis and in the inclination are major sources of systematic bias; it turns out that they should be determined with accuracies as good as $\simeq 0.1-1$ and $\simeq 1-10$ milliarcseconds, respectively.

gr-qc↗

arXiv2023

Bayesian conjugacy in probit, tobit, multinomial probit and extensions: A review and new results

A broad class of models that routinely appear in several fields can be expressed as partially or fully discretized Gaussian linear regressions. Besides including basic Gaussian response settings, this class also encompasses probit, multinomial probit and tobit regression, among others, thereby yielding to one of the most widely-implemented families of models in applications. The relevance of such representations has stimulated decades of research in the Bayesian field, mostly motivated by the fact that, unlike for Gaussian linear regression, the posterior distribution induced by such models does not seem to belong to a known class, under the commonly-assumed Gaussian priors for the coefficients. This has motivated several solutions for posterior inference relying on sampling-based strategies or on deterministic approximations that, however, still experience computational and accuracy issues, especially in high dimensions. The scope of this article is to review, unify and extend recent advances in Bayesian inference and computation for this class of models. To address such a goal, we prove that the likelihoods induced by these formulations share a common analytical structure that implies conjugacy with a broad class of distributions, namely the unified skew-normals (SUN), that generalize Gaussians to skewed contexts. This result unifies and extends recent conjugacy properties for specific models within the class analyzed, and opens avenues for improved posterior inference, under a broader class of formulations and priors, via novel closed-form expressions, i.i.d. samplers from the exact SUN posteriors, and more accurate and scalable approximations from VB and EP. Such advantages are illustrated in simulations and are expected to facilitate the routine-use of these core Bayesian models, while providing a novel framework to study theoretical properties and develop future extensions.

stat.ME↗

arXiv2022

Scalable and Accurate Variational Bayes for High-Dimensional Binary Regression Models

Modern methods for Bayesian regression beyond the Gaussian response setting are often computationally impractical or inaccurate in high dimensions. In fact, as discussed in recent literature, bypassing such a trade-off is still an open problem even in routine binary regression models, and there is limited theory on the quality of variational approximations in high-dimensional settings. To address this gap, we study the approximation accuracy of routinely-used mean-field variational Bayes solutions in high-dimensional probit regression with Gaussian priors, obtaining novel and practically relevant results on the pathological behavior of such strategies in uncertainty quantification, point estimation and prediction. Motivated by these results, we further develop a new partially-factorized variational approximation for the posterior of the probit coefficients which leverages a representation with global and local variables but, unlike for classical mean-field assumptions, it avoids a fully factorized approximation, and instead assumes a factorization only for the local variables. We prove that the resulting approximation belongs to a tractable class of unified skew-normal densities that crucially incorporates skewness and, unlike for state-of-the-art mean-field solutions, converges to the exact posterior density as p goes to infinity. To solve the variational optimization problem, we derive a tractable CAVI algorithm that easily scales to p in the tens of thousands, and provably requires a number of iterations converging to 1 as p goes to infinity. Such findings are also illustrated in extensive empirical studies where our novel solution is shown to improve the approximation accuracy of mean-field variational Bayes for any n and p, with the magnitude of these gains being remarkable in those high-dimensional p>n settings where state-of-the-art methods are computationally impractical.

stat.ME↗

arXiv2022

Extended Stochastic Block Models with Application to Criminal Networks

Reliably learning group structures among nodes in network data is challenging in several applications. We are particularly motivated by studying covert networks that encode relationships among criminals. These data are subject to measurement errors, and exhibit a complex combination of an unknown number of core-periphery, assortative and disassortative structures that may unveil key architectures of the criminal organization. The coexistence of these noisy block patterns limits the reliability of routinely-used community detection algorithms, and requires extensions of model-based solutions to realistically characterize the node partition process, incorporate information from node attributes, and provide improved strategies for estimation and uncertainty quantification. To cover these gaps, we develop a new class of extended stochastic block models (ESBM) that infer groups of nodes having common connectivity patterns via Gibbs-type priors on the partition process. This choice encompasses many realistic priors for criminal networks, covering solutions with fixed, random and infinite number of possible groups, and facilitates the inclusion of node attributes in a principled manner. Among the new alternatives in our class, we focus on the Gnedin process as a realistic prior that allows the number of groups to be finite, random and subject to a reinforcement process coherent with criminal networks. A collapsed Gibbs sampler is proposed for the whole ESBM class, and refined strategies for estimation, prediction, uncertainty quantification and model selection are outlined. The ESBM performance is illustrated in realistic simulations and in an application to an Italian mafia network, where we unveil key complex block structures, mostly hidden from state-of-the-art alternatives.

stat.ME↗

arXiv2022

Scalable computation of predictive probabilities in probit models with Gaussian process priors

Predictive models for binary data are fundamental in various fields, and the growing complexity of modern applications has motivated several flexible specifications for modeling the relationship between the observed predictors and the binary responses. A widely-implemented solution is to express the probability parameter via a probit mapping of a Gaussian process indexed by predictors. However, unlike for continuous settings, there is a lack of closed-form results for predictive distributions in binary models with Gaussian process priors. Markov chain Monte Carlo methods and approximation strategies provide common solutions to this problem, but state-of-the-art algorithms are either computationally intractable or inaccurate in moderate-to-high dimensions. In this article, we aim to cover this gap by deriving closed-form expressions for the predictive probabilities in probit Gaussian processes that rely either on cumulative distribution functions of multivariate Gaussians or on functionals of multivariate truncated normals. To evaluate these quantities we develop novel scalable solutions based on tile-low-rank Monte Carlo methods for computing multivariate Gaussian probabilities, and on mean-field variational approximations of multivariate truncated normals. Closed-form expressions for the marginal likelihood and for the posterior distribution of the Gaussian process are also discussed. As shown in simulated and real-world empirical studies, the proposed methods scale to dimensions where state-of-the-art solutions are impractical.

stat.CO↗