Neural networks have shown state-of-the-art performances in various classification and regression tasks. Rectified linear units (ReLU) are often used as activation functions for the hidden layers in a neural network model. In this article, we establish the connection between the Poisson hyperplane processes (PHP) and two-layer ReLU neural networks. We show that the PHP with a Gaussian prior is an alternative probabilistic representation to a two-layer ReLU neural network. In addition, we show that a two-layer neural network constructed by PHP is scalable to large-scale problems via the decomposition propositions. Finally, we propose an annealed sequential Monte Carlo algorithm for Bayesian inference. Our numerical experiments demonstrate that our proposed method outperforms the classic two-layer ReLU neural network. The implementation of our proposed model is available at https://github.com/ShufeiGe/Pois_Relu.git.

Class imbalance significantly degrades classification performance, yet its effects are rarely analyzed from a unified theoretical perspective. We propose a principled framework based on three fundamental scales: the imbalance coefficient $η$, the sample--dimension ratio $κ$, and the intrinsic separability $Δ$. Starting from the Gaussian Bayes classifier, we derive closed-form Bayes errors and show how imbalance shifts the discriminant boundary, yielding a deterioration slope that predicts four regimes: Normal, Mild, Extreme, and Catastrophic. Using a balanced high-dimensional genomic dataset, we vary only $η$ while keeping $κ$ and $Δ$ fixed. Across parametric and non-parametric models, empirical degradation closely follows theoretical predictions: minority Recall collapses once $\log(η)$ exceeds $Δ\sqrtκ$, Precision increases asymmetrically, and F1-score and PR-AUC decline in line with the predicted regimes. These results show that the triplet $(η,κ,Δ)$ provides a model-agnostic, geometrically grounded explanation of imbalance-induced deterioration.

Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics. Inference on graph-structured data requires methods that are permutation-invariant, scalable across varying sizes and sparsities, and capable of capturing complex long-range dependencies, making posterior estimation on graph parameters particularly challenging. Amortized Bayesian Inference (ABI) is a simulation-based framework that employs generative neural networks to enable fast, likelihood-free posterior inference. We adapt ABI to graph data to address these challenges to perform inference on node-, edge-, and graph-level parameters. Our approach couples permutation-invariant graph encoders with flexible neural posterior estimators in a two-module pipeline: a summary network maps attributed graphs to fixed-length representations, and an inference network approximates the posterior over parameters. In this setting, several neural architectures can serve as the summary network. In this work we evaluate multiple architectures and assess their performance on controlled synthetic settings and two real-world domains -- biology and logistics -- in terms of recovery and calibration.

Mixture-of-Experts (MoE) is a flexible framework that combines multiple specialized submodels (``experts''), by assigning covariate-dependent weights (``gating functions'') to each expert, and have been commonly used for analyzing heterogeneous data. Existing statistical MoE formulations typically assume constant coefficients, for covariate effects within the expert or gating models, which can be inadequate for longitudinal, spatial, or other dynamic settings where covariate influences and latent subpopulation structure evolve across a known dimension. We propose a Varying-Coefficient Mixture of Experts (VCMoE) model that allows all coefficient effects in both the gating functions and expert models to vary along an indexing variable. We establish identifiability and consistency of the proposed model, and develop an estimation procedure, label-consistent EM algorithm, for both fully functional and hybrid specifications, along with the corresponding asymptotic distributions of the resulting estimators. For inference, simultaneous confidence bands are constructed using both asymptotic theory for the maximum discrepancy between the estimated functional coefficients and their true counterparts, and with bootstrap methods. In addition, a generalized likelihood ratio test is developed to examine whether a coefficient function is genuinely varying across the index variable. Simulation studies demonstrate good finite-sample performance, with acceptable bias and satisfactory coverage rates. We illustrate the proposed VCMoE model using a dataset of single nucleus gene expression in embryonic mice to characterize the temporal dynamics of the associations between the expression levels of genes Satb2 and Bcl11b across two latent cell subpopulations of neurons, yielding results that are consistent with prior findings.

We revisit Deep Linear Discriminant Analysis (Deep LDA) from a likelihood-based perspective. While classical LDA is a simple Gaussian model with linear decision boundaries, attaching an LDA head to a neural encoder raises the question of how to train the resulting deep classifier by maximum likelihood estimation (MLE). We first show that end-to-end MLE training of an unconstrained Deep LDA model ignores discrimination: when both the LDA parameters and the encoder parameters are learned jointly, the likelihood admits a degenerate solution in which some of the class clusters may heavily overlap or even collapse, and classification performance deteriorates. Batchwise moment re-estimation of the LDA parameters does not remove this failure mode. We then propose a constrained Deep LDA formulation that fixes the class means to the vertices of a regular simplex in the latent space and restricts the shared covariance to be spherical, leaving only the priors and a single variance parameter to be learned along with the encoder. Under these geometric constraints, MLE becomes stable and yields well-separated class clusters in the latent space. On images (Fashion-MNIST, CIFAR-10, CIFAR-100), the resulting Deep LDA models achieve accuracy competitive with softmax baselines while offering a simple, interpretable latent geometry that is clearly visible in two-dimensional projections.

We show that for unconstrained Deep Linear Discriminant Analysis (LDA) classifiers, maximum-likelihood training admits pathological solutions in which class means drift together, covariances collapse, and the learned representation becomes almost non-discriminative. Conversely, cross-entropy training yields excellent accuracy but decouples the head from the underlying generative model, leading to highly inconsistent parameter estimates. To reconcile generative structure with discriminative performance, we introduce the \emph{Discriminative Negative Log-Likelihood} (DNLL) loss, which augments the LDA log-likelihood with a simple penalty on the mixture density. DNLL can be interpreted as standard LDA NLL plus a term that explicitly discourages regions where several classes are simultaneously likely. Deep LDA trained with DNLL produces clean, well-separated latent spaces, matches the test accuracy of softmax classifiers on synthetic data and standard image benchmarks, and yields substantially better calibrated predictive probabilities, restoring a coherent probabilistic interpretation to deep discriminant models.

Bayesian model selection commonly relies on Laplace approximation or the Bayesian Information Criterion (BIC), which assume that the effective model dimension equals the number of parameters. Singular learning theory replaces this assumption with the real log canonical threshold (RLCT), an effective dimension that can be strictly smaller in overparameterized or rank-deficient models. We study linear-Gaussian rank models and linear subspace (dictionary) models in which the exact marginal likelihood is available in closed form and the RLCT is analytically tractable. In this setting, we show theoretically and empirically that the error of Laplace/BIC grows linearly with (d/2 minus lambda) times log n, where d is the ambient parameter dimension and lambda is the RLCT. An RLCT-aware correction recovers the correct evidence slope and is invariant to overcomplete reparameterizations that represent the same data subspace. Our results provide a concrete finite-sample characterization of Laplace failure in singular models and demonstrate that evidence slopes can be used as a practical estimator of effective dimension in simple linear settings.

Clinical decision-making demands uncertainty quantification that provides both distribution-free coverage guarantees and risk-adaptive precision, requirements that existing methods fail to jointly satisfy. We present a hybrid Bayesian-conformal framework that addresses this fundamental limitation in healthcare predictions. Our approach integrates Bayesian hierarchical random forests with group-aware con-formal calibration, using posterior uncertainties to weight conformity scores while maintaining rigorous coverage validity. Evaluated on 61,538 admissions across 3,793 U.S. hospitals and 4 regions, our method achieves target coverage (94.3% vs 95% target) with adaptive precision: 21% narrower intervals for low-uncertainty cases while appropriately widening for high-risk predictions. Critically, we demonstrate that well-calibrated Bayesian uncertainties alone severely under-cover (14.1%), highlighting the necessity of our hybrid approach. This framework enables risk-stratified clinical protocols, efficient resource planning for high-confidence predictions, and conservative allocation with enhanced oversight for uncertain cases, providing uncertainty-aware decision support across diverse healthcare settings.

Identification and Estimation under Multiple Versions of Treatment: Mixture-of-Experts Approach Kohei Y oshikawa Shuichi Kawano January 5, 2026 Abstract The Stable Unit Treatment Value Assumption (SUTV A) includes the condition that there are no multiple versions of treatment in causal inference. Though we could not control the implementation of treatment in observational studies, multiple versions may exist in the treatment. It has been pointed out that ignoring such multiple versions of treatment can lead to biased estimates of causal effects, but a causal inference framework that explicitly deals with the unbiased identification and estimation of version-specific causal effects has not been fully developed yet. Thus, obtaining a deeper understanding for mechanisms of the complex treatments is difficult. In this paper, we introduce the Mixture-of-Experts framework into causal inference and develop a methodology for estimating the causal effects of latent versions. This approach enables explicit estimation of version-specific causal effects even if the versions are not observed. Numerical experiments demonstrate the effectiveness of the proposed method. Keywords causal inference multiple versions of treatment compound treatments mixture-of-experts EM algorithm 1 Introduction In the theory of causal inference, a fundamental starting point is the potential outcomes framework since Rubin (1980), whose core assumption is the Stable Unit Treatment Value Assumption (SUTV A).

Numerical simulation of complex physical phenomena is a core enabling technology for digital twins, which are comprised of physical and virtual assets with a two-way flow of information: data from the physical asset is used to construct and/or calibrate the virtual asset (a numerical model), while numerical predictions from the virtual asset are used for control or decision-making for the physical asset [42]. To be viable for practical application, the virtual asset must be able to produce predictions rapidly and reliably; however, the underlying physics that are of interest for digital twin applications can typically only be accurately simulated using a large number of degrees of freedom, leading to computationally expensive numerical simulations. The explainability and computational efficiency of decisions made by the digital twin play a key role in safety-critical applications, making explainable artificial intelligence an essential ingredient [24]. Model reduction techniques are one such explainable scientific machine learning technique that construct low-dimensional systems, called reduced-order models (ROMs), to serve as computationally inexpensive surrogates for a high-dimensional physics simulation [4, 20]. This paper introduces a technique for adaptively constructing ROMs to emulate systems with parametric dependence, that is, systems whose behavior varies with some set of parameters, usually representing physical properties. We focus on systems where the parametric dependence manifests in the operators defining the model, not merely in initial conditions or external inputs.