Papers

The SLGP package provides nonparametric estimation of fields of probability densities indexed by covariates, from unevenly sized samples with few or no replicates. A Spatial Logistic Gaussian Process applies a logistic density transformation to a finite-rank Gaussian process over a joint index-response domain, yielding a prior over conditional densities that adapts in location, shape, and modality. The contribution of this paper is the implementation: a finite-rank Random-Fourier-Feature representation that keeps the transformed process numerically tame, a log-concave likelihood that makes the fit a convex problem, and a family of quadrature shortcuts for the normalising integrals that turn a per-observation cost into a per-grid cost. Three estimation modes are available: MAP, Laplace, and full MCMC. We demonstrate the package throughout on the classical Fiji-Tonga earthquake catalogue, estimating how the distribution of hypocentre depths deforms across the region, and on a discrete-response variant.

We consider binary prediction with i.i.d. contexts from an unknown distribution and adaptively chosen losses. We show that a simple Follow-the-Perturbed-Leader algorithm using a Gaussian perturbation for each observed context achieves $\widetilde O(\sqrt{T\log N})$ regret for a class of $N$ experts, while requiring one optimization-oracle call per round and no explicit enumeration of the class. For an infinite hypothesis class $\mathcal H$, the same algorithm achieves $\widetilde O(\sqrt{T\operatorname{VC}(\mathcal H)})$ regret. This resolves an open problem posed by Lazaric and Munos (2012), showing that hybrid classification is computationally as easy as statistical learning. As an application, we reduce the problem of contextual bandits with $K$ actions to classification through uniform exploration, achieving $\widetilde O(K^{2/3}T^{2/3}(\log N)^{1/3})$ regret. This matches the best known dependence on the horizon while removing the context-distribution access required by prior oracle-efficient methods.

NBA athlete performance tends to increase through early career as athletes develop and acclimate to the league, followed by decline due to age-related deterioration in athleticism. While this general pattern persists, the precise shape of this trajectory varies by athlete and across different measures of performance. To model performance increase and decline, we introduce the concave process prior, a novel nonparametric prior over concave functions. We then use a latent variable model to characterize dependence in aging profiles across player-metrics, embedding each player in a shared low-dimensional latent space so that players with similar profiles learn similar trajectory shapes, peak ages, and peak values. Posterior analysis of the learned embedding supports latent-space nearest-neighbor retrieval of career-comparable players and informed projections of young players. We apply our model to data across over a dozen performance metrics for over two thousand players in seasons ranging from 1997 to 2026. Our results show that jointly modeling all metrics improves held-out predictive performance over single-metric alternatives, and that the concavity constraint itself improves prediction. We find that athleticism-driven metrics such as blocks and offensive rebounds peak in a player's early twenties, while skill-based shooting metrics peak in the mid-twenties or later.

Inverse Optimal Transport (OT) based methods for representation learning learn representations such that the global OT coupling between a pair of data marginals in the representation space, concentrates on the positive pairs. This is in contrast to previous methods that primarily focused on pairwise matching. However, these methods $\textit{DO NOT}$ utilize negative pairs and hence are not truly contrastive in their approach. We show that this leads to issues of dimensional collapse and hence degraded downstream performance. To alleviate this, we develop a novel multi-marginal (MM) inverse OT (IOT) contrastive learning (CL) approach called Neg-MMIOT-CL, which learns representations such that the global multi-marginal OT (MMOT) coupling between a triple of data marginals, with respect to a carefully designed ground-cost between triplets of data points in the representation space, concentrates on the anchor-positive-negative $\textit{triplets}$. For a latent class model, we empirically show that Neg-MMIOT-CL alleviates dimensional collapse. Furthermore, for a specific choice of ground cost for all triplets in representation space, we prove that the optimal representation configuration for Neg-MMIOT-CL exhibits equiangular property for within-class and across-class representations, which translates to Neural-Collapse when the representation dimension is larger than the number of classes minus one – a result that is $\textit{previously established only}$ for pairwise contrastive learning methods. Finally, we propose Neg-IOT-CL-PushPull, that is a computationally efficient alternative to Neg-MMIOT-CL, alleviating the high cost of computing MMOT plans needed during implementation. We apply these methods on both synthetic and real-world datasets and show significant improvements over existing OT-based contrastive learning methods.

Estimating causal effects with continuous treatments in observational studies is challenging due to confounding, model misspecification, and high-dimensional covariates. We propose the Weighted Spline-Expanded Network (WSENet), an end-to-end neural framework that addresses these challenges by combining covariate balancing, structured treatment embedding, and bias-corrected outcome estimation. WSENet first applies Distance Covariate Optimal Weights to induce distributional independence between covariates and treatment without relying on parametric models. It then learns the conditional outcome via a structured network that fuses outcome-relevant representations of covariates with a spline-expanded treatment input, enabling smooth and flexible modeling of the dose-response relationship. To mitigate residual bias, we introduce Weighted Targeted Regularization, a correction technique based on efficient influence functions that yields a doubly robust estimator. Extensive evaluations on semi-synthetic and real-world datasets, including high-dimensional genomic and environmental health data, demonstrate that WSENet consistently outperforms existing baselines in both accuracy and stability.

Groups differing in social and economic circumstances often differ markedly in depressive symptom levels, yet their estimated symptom networks show few clear differences. Such null results are often read as evidence that the groups' symptom systems are the same, but they only show that no difference was detected in how symptoms interact. How readily symptoms become present, and how this depends on the contextual conditions under which they are observed, is rarely compared. Building on a slow-fast perspective, we treat depressive symptoms as a relatively fast-changing system embedded in more persistent social, economic, psychosocial, health, and lifestyle conditions that shape symptom activation. Using a cohort of 23,689 adults from Amsterdam, we illustrate this with PHQ-9 depressive symptoms and a composite index of persistent socioeconomic, psychosocial, and health-related conditions, which we call Slow Risk Load (SRL). Participants with high SRL had substantially higher symptom levels than those with low SRL. A standard Network Comparison Test detected no overall difference in network structure, although global strength was modestly higher in the high-SRL group. Ising models, which separate how symptoms co-occur from how readily each becomes present, indicate higher activation under high SRL for eight of nine symptoms, and model comparison consistently favored group-specific activation over group-specific interactions. The slow-fast perspective reframes group network comparisons as a multiple-timescale problem in which network structure, symptom activation, and context should be considered jointly. It places symptom-focused and context-focused interventions at different layers of the same coupled system rather than in competition.

Covariates are widely used in randomized experiments to improve precision. However, in the presence of interference, where outcomes may depend on the treatment assignments of other units, standard covariate adjustment methods may fail to preserve desirable properties such as the no-harm property, meaning that incorporating covariates does not worsen estimator performance. Existing approaches that incorporate covariates under interference typically rely on specifying a particular interference structure, and their guarantees can be sensitive to misspecification. In this paper, we study how to incorporate covariate information in a way that preserves the no-harm property while remaining largely agnostic to the underlying interference structure. We focus on the estimation of the expected average treatment effect (EATE) using the Hájek estimator and study rerandomization under interference, a design-stage procedure that restricts the assignment space to allocations with sufficiently small covariate imbalance. Our framework also allows the covariates used for rerandomization to depend on the treatment assignment itself, such as the proportion of treated neighbors, which naturally arises in settings with interference. We show that, even under interference, rerandomization can improve estimation precision asymptotically relative to unrestricted Bernoulli randomization, relying only on mild conditions on the dependence structure across units. When a conservative dependence graph is available, we further develop an optimization-based conservative variance estimator for inference under rerandomization.

Knowledge Distillation (KD) has emerged as a vital paradigm for transferring the capabilities of high-capacity models to efficient “student” counterparts, addressing critical challenges in computational cost, deployment constraints, and privacy-sensitive settings. Although KD is widely used in practice, it is often viewed primarily as an engineering technique, with a unified statistical perspective remaining less developed. This review bridges that gap by presenting a unified Bayesian formulation of KD that formulates teacher predictions as prior information. This provides a principled interpretation of how teacher information is incorporated into student learning and establishes a rigorous connection to uncertainty quantification. We demonstrate how this foundational lens reconciles classical distillation with modern extensions in generative and foundation-model systems, showing that contemporary developments remain rooted in these same statistical principles. By synthesizing theory with emerging methodologies and diverse applications, this review provides a conceptual roadmap and identifies critical open problems for the future of the field.

Continually adapting models to new tasks requires retaining earlier knowledge under limited memory and computation. Experience replay addresses this challenge, but priorities based on individual loss increases overlook how related memories respond to the same update and can overemphasize isolated responses. We introduce SPatial coHErent risk control for REplay (SPHERE), a general replay-allocation method applicable across a broad range of learning settings. SPHERE uses a representation kernel to aggregate signed prospective loss changes, attenuating unsupported spikes while retaining coherent increases. It then formulates allocation as entropy-regularized transport, redistributing uniform source mass toward supported high-risk regions while penalizing long-distance transfers. We derive replay coefficients from the transport objective's sensitivity to the original loss changes and blend them with uniform replay to maintain baseline rehearsal. Our analysis establishes conditions under which kernel aggregation improves risk estimation and bounds transport-value inflation due to residual noise and smoothing bias. Experiments demonstrate that SPHERE improves accuracy and reduces forgetting across noisy-label vision tasks, continual language-model instruction tuning, and code-generation reinforcement learning with incomplete test rewards.

Understanding why predictors can generalize despite interpolating noisy training data is a central puzzle in machine learning. Most work on such "benign overfitting" studies minimum-2-norm linear regression, reflecting the inductive bias of gradient descent. However, modern optimizers such as Adam and Muon use non-Euclidean update geometries, favoring solutions associated with other norms. Analyzing regression for non-Euclidean norms is substantially more difficult, with known results essentially limited to Gaussians. In this paper, we develop a method to analyze benign overfitting in linear regression for general norms and general (sub-Gaussian) distributions. As a special case, we prove that minimum-p-norm interpolation with p>1 can benignly overfit even for non-Gaussian distributions, under suitable conditions. Perhaps surprisingly, for the 1-norm, benign overfitting does not hold in general for well-behaved (but non-Gaussian) distributions, showing that existing positive 1-norm results rely crucially on Gaussianity. Our proof analyzes the geometry of the dual optimization problem, using concentration and central limit tools to show it is approximately Euclidean in many high-dimensional cases.

Historically, statistical analysis of offensive lineman has been hindered by the lack of easily measurable quantities. More recently, with the introduction of player tracking data new methodological advances are now possible. Using high-dimensional spatio-temporal data, we adapt the defensive-matchup hidden Markov model of \cite{franks2015characterizing} from basketball to football pass protection, producing frame-by-frame probabilistic assignments of each pass blocker to the rushers. We show how this probabilistic assignment is a usable modeling artifact that augments existing player-evaluation frameworks. We directly quantify the attention a rusher commands, upgrade adjusted plus-minus \citep{Macdonald+2012} from all-or-nothing stints to partial, continuous blocking credit in continuous time, yield block-shedding survival metrics, and measure the space a rusher generates for his teammates. Fit to the first eight weeks of the 2021 NFL season, the resulting metrics recover widely-recognized elite rushers and pass protectors and align with independent charting.

We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs). A key challenge for probability estimation is defining a tractable distribution over the input space. To accomplish that, RareTrap uses a surrogate LLM and constructs a geometry-aware mapping from a lower-dimensional latent reference space into its token-embedding space to induce an explicit and reproducible distribution over input prompts. A response-level performance function is utilized on the response to quantify behavior severity. This enables sequential rare event simulation that concentrates evaluations on progressively more severe behaviors while preserving probability under the induced prompt distribution, which would otherwise be prohibitive to measure. Across 10 open-weight and two frontier models (GPT-5.4 and Claude Sonnet 4.6), we find that RareTrap successfully induces severe resource consumption behaviors and computes their probability with as few as 200 evaluations. RareTrap provides model developers a principled approach for evaluating language models under a common distribution, and prioritizing alignment effort to improve safety and mitigate risks.

Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement. Yet recurrent forecasting models typically treat observations as inputs that directly control their latent dynamics. It leads to a regime change when these observations become unavailable at prediction time. Following a state-estimation perspective, we introduce Observer State-Space Models (OSSMs), a class of recurrent models that interprets the observed input time series as measurements of an underlying autonomous dynamical system. OSSMs explicitly separate latent-state propagation from measurement assimilation: a single transition governs the dynamics across both context and forecasting intervals, while available observations correct the estimated state through an observer. This formulation naturally exposes classical control-theoretic properties, including observability and convergence of the state estimation error. We further show that conventional and recent SSMs can be recovered as particular instances of our OSSM framework, thereby providing a unified interpretation of their recurrent dynamics and revealing modeling inconsistencies. We perform experiments across several benchmarks showing that OSSM achieves substantial improvements while maintaining the same parameter count and training setup as the corresponding SSM baseline. These results support a simple principle for recurrent forecasting: observations should correct the estimated latent state, rather than control the dynamics used to propagate it.

Automatic relevance determination (ARD) is the standard device for input selection in Gaussian process (GP) regression. By giving the covariance kernel a separate lengthscale for every input and learning those lengthscales by maximizing the marginal likelihood, ARD lets the data decide which coordinates matter: irrelevant inputs receive very large lengthscales and are effectively switched off. We trace this mechanism to the Bayesian Occam's razor embodied in the marginal likelihood, derive the gradient through which it prunes inputs, and emphasize that ARD delivers effective rather than exact sparsity. We review the algorithms used in practice and the rules that turn lengthscales into selections, and we survey the asymptotic theory, distinguishing the fixed-domain identifiability obstruction on the lengthscales from the high-dimensional selection-consistency guarantees recently established for hierarchical GP priors, and noting what remains open for plain ARD. We compare ARD with spike-and-slab priors, sparse axis-aligned and global-local shrinkage priors including the Bayesian lasso and horseshoe, penalized likelihood kriging, sensitivity and projection criteria, and additive kernels. We argue that ARD endures because of its seamless integration with kernel learning, universal software support, and low cost, and we close with its limitations and remedies.

Automatic relevance determination (ARD), the default tool for variable selection in Gaussian-process (GP) regression, ranks inputs by inverse lengthscales – which measure how fast a function varies, not how much an input contributes to prediction – and offers no calibrated rule for deciding which inputs to keep. The prediction-centred alternative, the derivative sensitivity $\nu_j = \mathbb{E}[(\partial f/\partial x_j)^2]$, is available in closed form from a fitted GP, but turning it into a selection rule is harder than it looks: at a null input the estimator is a degenerate quadratic form, so Wald and Bernstein-von Mises cutoffs are anti-conservative, and the natural residual bootstrap is mis-scaled. We show that a studentized multiplier bootstrap of the GP derivative process repairs both, prove its validity through an invariance principle for quadratic forms, and obtain asymptotic family-wise and false-discovery-rate control across inputs. Over 100 replications the rule controls FDR wherever inputs are truly null, while uncalibrated derivative rankings breach the target by up to 2x and a Bernstein-von Mises cutoff by 2.2x; at matched FDR it loses no power; it holds under a Matérn kernel and input correlation up to 0.99; on real data with planted and authentic null inputs it admits 5-12x fewer spurious inputs; it costs 5-18% of the GP fit; and a block-averaged variant retains validity at cost linear in $n$.

Transformers have emerged as powerful architectures for learning solution operators of physical systems. Empirically the prediction error has been observed to decrease when the data size and model size increase, suggesting neural scaling behavior. Yet a theoretical understanding of such scaling laws for transformer-based operator learning remains limited. In this work, we develop a theoretical framework for characterizing the approximation and generalization errors of transformer-based operator learning. Our analysis builds on a local-to-global approximation principle that is naturally aligned with the softmax attention mechanism and yields discretization-invariant output functions. On approximation theory, we derive a universal approximation error of transformer-based operator learning for Hölder-regular operators. On generalization theory, we establish a power scaling law between the prediction error and the training data size. The rate of convergence represented by the scaling exponent explicitly reflects the dimensions of the input and output domains, the regularity of the underlying functions and operators, and crucially, the intrinsic dimension of the input function class. By exploiting this intrinsic low-dimensional structure, our analysis yields a power-law generalization rate for operator learning, in contrast to the logarithmic-type power-law rates appearing in existing analyses of operator learning with feedforward neural networks. Numerical experiments validate the predicted power-law scaling and confirm that the convergence rate varies systematically with the intrinsic dimension of the input function class.

Critical slowing down (CSD), the slowing of recovery from perturbations as a system approaches a critical transition, is widely used for early warning, but whether such signals appear in environmental transitions subject to rapidly changing external forcing has rarely been tested with observations. Here we show, using 2,427 icing-onset events in 1-min observations from 121 South Korean road weather stations, that such signals do not consistently precede road icing. Icing began from different prior surface states, but conditions at onset varied continuously with weak separation among pathways. Cold dose, deposition dose and freeze-thaw accumulation at onset exceeded those at non-icing control times, with cold-dose discrimination highest at decay timescales of 30 min or less. However, the increases in variance and lag-1 autocorrelation expected under CSD did not distinguish icing from control times; the same procedure recovered these increases in synthetic series with a declining recovery rate, and the null result was replicated for 3,091 events at 127 independent stations. Predictive information was nevertheless present: adding recent changes and cumulative antecedent conditions to current conditions improved discrimination, and surrounding meteorological fields increased the area under the ROC curve by 0.030-0.032 for forecast windows of 1 to 12 h and reduced false alarms by 62-67% at 3 and 6 h. These results suggest that road icing is more consistent with recent meteorological forcing moving the road surface into icing-favourable conditions than with a progressive decline in internal stability, and they indicate where early warning should look when a transition is externally forced.

Metric graphs are generalisations of linear networks and provide a natural framework for the definition of continuously-indexed Gaussian processes. We define a new class of distances on these topologies, termed polyharmonic distances, which unify and extend the spectral construction underlying the effective resistance distance and the biharmonic one. We give both a spectral and a variational characterisation. Furthermore, we show an explicit class of stochastic processes whose variograms coincide with the squared polyharmonic distances. Finally, we show how these metrics can be composed with suitable completely monotonic functions to define isotropic processes having any prescribed finite-order mean-square differentiability along the edges and satisfying the Kirchhoff conditions up to order one at the vertices.

Many probabilistic predictors must satisfy exact structure in every stochastic realization, yet common hard-constraint approaches form predictions in ambient coordinates and then correct or project them. We introduce SLP-ProbHard, a cross-family, representation-centered framework for probabilistic hard-constrained learning when explicit structural parameterizations are available. Its core object, a Structural Feasible Latent Parameterization (SFLP), combines a structural latent law $Z \sim P^Z_\theta(\cdot\mid x)$ with a feasible map $Y=h_\phi(x,Z)$ that satisfies the constraint for every latent realization. Together these components define the predictive law itself, including its support and boundary probabilities, rather than serving as a final feasibility wrapper. We study how feasible coordinates and maps affect stochastic dimension, dependence, calibration, expressiveness, and computation. Experiments use Gaussian latent laws and fixed geometry-derived maps across affine equalities, ordering and simplex constraints, nonlinear manifolds, and three structural representations of seven-basin hydrological flow-duration-curve (FDC) data. In an official-source affine comparison with ProbHardE2E/DPPL, both methods achieve zero practical constraint violations. SLP-ProbHard uses 8 instead of 11 stochastic coordinates and improves MSE/MAE, while DPPL yields better marginal CRPS and closer-to-nominal coverage; a paired test detects no Energy Score difference across ten seeds. Real-world affine and nonlinear FDC representations reduce 13 to 7 and 14 to 8 ambient versus computational coordinates, respectively. Exact feasibility alone thus does not determine a predictive law, motivating direct structural generation when meaningful feasible coordinates are available.

Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide flexible tools for generative-model-based CI tests, which rely on an estimated conditional distribution to generate randomized samples. However, errors in estimating this distribution accumulate in existing Type I error bounds, and consistency of the generative estimator alone does not guarantee asymptotic Type I error control. To address this limitation, we formulate conditional generative modeling as a domain adaptation problem and leverage auxiliary data from multiple source domains to improve estimation in the target CI testing domain. We propose Domain-Adapted Diffusion (DA-Diff), a multi-source domain adaptation framework for conditional diffusion models based on weighted empirical risk minimization over both target and source domains. We establish the convergence rate of DA-Diff and show how transferable source data can improve target-domain estimation through an increased effective sample size while controlling transfer bias. Building on DA-Diff, we further propose Domain-Adapted Conditional Independence Testing (DA-CIT) and show that its Type I error satisfies $P(p \leq \alpha) \leq \alpha + o(1)$. Experiments demonstrate that DA-Diff improved conditional generation quality compared with transfer-learning diffusion baselines, while DA-CIT provides strong Type I error control and competitive power.

Conformal prediction provides distribution-free finite-sample marginal coverage, but post-hoc calibration data may be too scarce to learn how uncertainty varies across inputs. Meanwhile, abundant covariates can often be labeled cheaply by domain models or general-purpose language models. We study whether these synthetic labels can improve conditional coverage when only a small trusted sample is available. Building on score-quantile regression, we introduce prediction-powered quantile learning: a synthetic-labeled pool estimates pinball risk, paired trusted and synthetic outcomes correct its bias, and an independent trusted split performs final conformalization. Profiling pinball risk over scalar corrections reveals that population conditional-coverage error is its functional gradient; the corresponding Hessian removes global shifts and weights remaining shape error by boundary density. Composing this geometry with prediction-powered learning yields a three-resource expansion and a benefit–cost rule for synthetic power. Across eight regression benchmarks, synthetic-powered quantile learning substantially improves downstream conditional coverage while preserving marginal validity and producing more compact prediction sets. A human-rating study finds similar gains from external LLM labels and exposes a quality–quantity–cost tradeoff.

Weighted split conformal prediction reweights calibration scores by the likelihood ratio between the test and training covariate distributions and guarantees marginal coverage under covariate shift. We study its coverage conditional on the calibration data. An elementary argument, based on a single concentration inequality at a fixed population quantile, gives explicit training-conditional bounds without unspecified constants, and shows that the relevant scale is not the supremum of the likelihood ratio but a variance proxy built from the chi-squared divergence of the shift and from the average of the ratio over the part of the test population, of probability equal to the miscoverage level, where it is largest. A two-point lower bound shows that the root-m rate and the chi-squared contribution are intrinsic to the shift. Run at an explicitly inflated level, the weighted quantile becomes a deterministic PAC prediction set. We compare it with randomized rejection sampling and with importance-weighted learn-then-test and, through a certified choice of a clipping level for the likelihood ratio, map the regime in which each gives the narrower valid set. The analysis extends to estimated likelihood ratios and to tail functionals estimated from an unlabeled source sample, which yields a fully finite-sample certificate.

Locally stationary Markov chains have attracted a lot of attention in statistics in the past three decades. In this paper we prove a variety of limit theorems for partial sums generated by such chains. We first provide explicit formulas for the asymptotic mean and variance (and also higher moments), and obtain optimal convergence rates towards them. We then prove a Berry–Esseen theorem, a local central limit theorem, Edgeworth expansions, and large and moderate deviations principles. Our approach involves a parametric Perron–Frobenius theorem, which is proved using the theory of complex (Hilbert) projective metrics developed in \cite{Rugh,Dubois}, together with local approximation arguments and ideas in \cite{dolgopyat2023berry}.

Recovering probability measures from their moments has numerous applications, esp. in connection with the method of moments in statistics and optimization. In the setting where measure need not be finitely atomic, but its support is known to be compact and semialgebraic with codimension at least one, the problem is still open. We combine moment-matrix kernel information with the Christoffel–Darboux kernel to provide a discrete approximation of the support. To validate the proposed approach, we test our algorithm on analytically computed moments and pseudo-moments arising from polynomial optimization problems without unique global minimizers. This complements well-known recent work on recovery of measures with algebraic support, where the kernel of a moment matrix can reveal polynomials vanishing on the support, and on recovery of sufficiently regular full-dimensional supports, where estimators constructed by thresholding the Christoffel–Darboux kernel are known to converge asymptotically to the support.

We propose a new $L_2$-type test for white noise which allows the dimension $p$ of the time series to either (i) be a fixed constant, or (ii) diverge with the sample size $n$. The proposed test statistic exhibits an interesting phase transition, following two different regimes of behavior: $p$ is fixed, and $p\rightarrow\infty$. Because identification of the operable regime is difficult, if not impossible in practice, we devise a novel adaptive bootstrap method to construct unified testing procedure across different phases. Numerical experiments confirm the good finite sample performance of the proposed adaptive $L_2$-type test in comparison to the existing methods in the literature. The proposed testing procedure has been implemented in R package HDTSA.

A special semimartingale admits a unique decomposition $X=X_0+M+A$ into a local martingale $M$ and a predictable finite-variation part $A$. We consider the identification of $A$ when $X$ is observed only through repeated cross-sections. The estimand is then the projection of the sampled predictable compensator onto the observable feature filtration, namely the current state together with whatever randomness is shared across the population, so that at a fixed diffusion coefficient the marginal flow identifies the drift only up to a Markovian projection. If the drift is an affine functional of an observed lag window, the joint problem is a convex quadratic programme whose solution is the pseudo-panel regression of econometrics. Our principal concern is the case, which we believe not to have been treated before, in which the drift is the output of a hidden linear dynamical system whose dynamics are themselves to be identified from the marginals. The joint problem is then a bilinear quadratically constrained programme, which we solve to certified global optimality by spatial branch and bound; with unpenalised state disturbances and a drift basis growing with the grid it is NP-hard already in latent dimension one, by reduction from $\ell^1$ rank-one matrix approximation, whereas the complexity of the deterministic system at fixed latent dimension remains open. A block-coordinate decomposition offers a cheaper alternative. For the estimator itself, we obtain rates at a fixed mesh, separated into Monte-Carlo, estimation and grid contributions.

Streaming data, characterized by high volume, rapid arrival rates, and evolving distributions, have become increasingly prevalent in modern applications. Developing efficient and reliable estimation procedures is therefore essential for real-time statistical analysis. However, most existing online estimation methods rely on the assumption of batch homogeneity, which can be violated in practice due to abnormal batches, distributional shifts, or other forms of batch heterogeneity. To address this challenge, we develop renewable online expectile regression procedures for heterogeneous streaming data. Specifically, we propose two complementary strategies for handling abnormal batches: (1) a detection-based approach that employs a sequential monitoring mechanism based on score test statistics to identify and remove potentially abnormal batches; and (2) an adaptive-weighting approach that assigns data-driven weights to incoming batches, reducing the influence of abnormal or drifting batches while retaining information from reliable observations. Both strategies rely solely on score test statistics and can be seamlessly integrated into existing renewable estimation and inference frameworks without requiring additional structural assumptions. Furthermore, to enhance robustness against heavy-tailed errors and outliers, we replace the conventional l2 loss with the Huber loss and develop a robust extension of renew?able online expectile regression. Extensive simulation studies and analyses of clinical datasets demonstrate that the proposed methods achieve improved estimation accuracy and robustness in the presence of batch heterogeneity. Overall, the proposed framework provides a flexible and effective solution for renewable expectile regression in complex streaming data environments.

Background. Magnetic resonance imaging (MRI) is central to Alzheimer's disease research and clinical evaluation, yet timing of first MRI after cohort entry varies substantially. In aging cohorts, many participants die before imaging, and treating death as noninformative censoring can distort inference on neuroimaging access and conceal disparities. Objective. To quantify individual-level determinants and center-level heterogeneity in timing of first neuroimaging while accounting for the competing risk of death. Methods. We analyzed National Alzheimer's Coordinating Center Uniform Data Set v3 linked to MRI records from 2015 through March 2025. The study included 20,867 participants aged 50-95 years without dementia at baseline and with known APOE {\epsilon}4 status. Time from baseline to first post-baseline MRI was the primary event, with death before MRI treated as a competing event. We fit Bayesian multilevel cause-specific accelerated failure time models with Alzheimer's Disease Center random intercepts, using Weibull and log-logistic models for MRI timing and death, respectively. Frequentist accelerated failure time and Cox models were used for sensitivity analyses. Results. APOE {\epsilon}4 was not credibly associated with timing of first MRI. Older age, lower educational attainment, and non-White race were associated with delayed MRI acquisition. Center-level variation in MRI timing was substantial. Conversely, APOE {\epsilon}4 homozygosity was associated with earlier death prior to MRI, alongside strong effects of age and cognitive impairment. Conclusions. Timing of first MRI in Alzheimer's research cohorts is driven primarily by demographic, social, and center-level factors rather than genetic risk. Accounting for competing mortality and site heterogeneity is necessary to avoid biased neuroimaging samples and support equitable Alzheimer's research.

Many generative systems return multiple candidate responses and are evaluated according to the best one. Recent work shows that, when demonstrations are optimal, pass@$k$ can reduce the sample complexity of learning from demonstrations by a logarithmic factor in $k$. We ask what happens when the demonstrator is not assumed to be optimal. We find that multiple responses provide a qualitatively stronger benefit in this setting. In a finite reward-class model with no reward feedback, moving from pass@$1$ to any pass@$k$ with $k\ge2$ changes the worst-case dependence on target accuracy from $1/\varepsilon^2$ to $1/\varepsilon$, uniformly over demonstrator quality. Under standard evaluation, where an unknown reward is fixed before training, increasing $k$ provides an additional and distinct benefit: the optimal dependence on a reward class of size $N$ improves from $\log N$ to $\log N/\log k$. We further show that these two effects can be separated. Under robust evaluation, where one learned policy must compete with the demonstrator simultaneously for every reward in the class, the fast $1/\varepsilon$ dependence persists, while the $1/\log k$ improvement can disappear. We establish matching upper and lower bounds in the corresponding regimes and give a greedy multiplicative-weights learner achieving the upper bounds without any assumption on demonstrator quality.

We study robust reconstruction for the \(q\)-state Potts broadcast process on a Galton-Watson tree in the growing-alphabet regime \(q\to\infty\), with boundary depth growing sufficiently quickly in relation to \(q\). We show that, in the regime \(d\lambda >1\), where \(d\) is the expected number of offspring and \(\lambda\) is the nontrivial eigenvalue of the Potts transition matrix, the root posterior is asymptotically unchanged by a broad class of noise channels applied independently to the boundary labels. This remains true even when the probability of retaining the true label at an individual boundary vertex tends to zero as \(q\to\infty\). More precisely, under suitable moment and noise assumptions, the noiseless and noisy root posteriors converge to one another in expected total variation, and hence have the same asymptotic Bayes-optimal reconstruction accuracy.