Clay weekly context brief for the Statistics category (ISO week 2026-W34).

Clay tracks publications from the Statistics feed list. Below are recent items from this category, each with its source and a short description of what the publication covers when one is available in the source feed.

Recent publications:
1. On hypoellipticity of degenerate operators in testing and detection problems
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2510.22150
   We study a class of degenerate diffusion generators arising in sequential testing and quickest detection problems with partial information.
2. Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.12663
   Wildfire susceptibility mapping typically relies on physical variables assembled from multiple remote-sensing, climate, and geospatial products.
3. Accelerated Markov Chain Monte Carlo Algorithms on Discrete States
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2505.12599
   We propose a class of discrete state sampling algorithms based on Nesterov's accelerated gradient method, which extends the classical Metropolis-Hastings (MH) algorithm.
4. SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.12443
   Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group.
5. LLteacher: A Tool for the Integration of Generative AI into Statistics Assignments
   Source: stat.OT (Other Statistics)
   Link: https://arxiv.org/abs/2512.23053
   As generative AI becomes increasingly embedded in everyday life, the thoughtful and intentional integration of AI-based tools into statistics education has become essential.
6. Time-Varying Multi-Seasonal ARMA Models
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2608.11481
   We propose an ARMA model that allows for multiple seasonal periods and time varying parameters in both regular and seasonal components, building upon previous work for pure AR processes and the conditional likelihood.
7. Stable Central Limit Theorems for Discrete-time Lag Martingale Difference Arrays: Applications to Dynamic Causal Inference
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2510.06524
   Recent work in dynamic causal inference introduced a class of discrete-time stochastic processes that generalize martingale difference sequences and arrays as follows: the random variates in each sequence have expectation zero given certain lagged filtrations but not given the natural filtration.
8. When Method Choice Changes Statistical Inference: A Comparison of a Baseline Two-Stage Approach and Bayesian Joint Modeling for Longitudinal and Survival Data
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.12682
   The two-stage approach and Bayesian joint modeling are commonly used to analyze longitudinal biomarker measurements together with time-to-event outcomes.
9. Gradient Boosted Mixed Models: Flexible Estimation of Mean and Variance Components for Clustered Data
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2511.00217
   We introduce a novel way to combine gradient boosting with mixed effects models, whereby the mean and variance components are learned jointly as functions of covariates via likelihood-based gradients.
10. Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.12973
   In this paper, we study how to perform statistical inference for quantile temporal difference learning (QTD) in distributional reinforcement learning.
11. Reliability of decisions based on tests: Fourier analysis of Boolean decision functions
   Source: stat.OT (Other Statistics)
   Link: https://arxiv.org/abs/2007.05857
   Items in a test are often used as a basis for making decisions and such tests are therefore required to have good psychometric properties, like unidimensionality.
12. Causal inference for group-contaminated structured outcomes: observable quotients, lossless reduction and exact randomization inference
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2608.11954
   Structured potential outcomes such as microscopy images may be recorded after an unknown, unit-specific transformation.
13. Tree-structured Ising models under mean parameterization
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2507.18749
   In the risk modeling literature, the Ising model has emerged as a valuable framework for dependent Bernoulli random variables, as its underlying graphical structure captures complex dependence patterns.
14. Spatial similarity in socioeconomic data: a wavelet approach for England
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.13196
   Socioeconomic indicators in England exhibit complex spatial patterns that are not well captured by standard approaches based on averages or broad geographic classifications.
15. Minimum Covariance Determinant Estimator and Outlier Detection for Interval-valued Data
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2604.26769
   Interval-valued data are one of the most common symbolic data types, which enables the preservation of the underlying variability of the data.
16. Statistical Properties of Robust Learning under Distributional Shifts
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.13133
   Distributional shifts arise when the target deployment environment differs from the source environment that generated the training data.
17. leaspy: LEArning Spatiotemporal Patterns in PYthon
   Source: stat.OT (Other Statistics)
   Link: https://arxiv.org/abs/2608.09365
   Longitudinal data are fundamental across scientific disciplines for modeling how complex systems evolve over time.
18. Sample size determination for win statistics in cluster-randomized trials
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2510.22709
   Composite endpoints are increasingly used in clinical trials to capture treatment effects across multiple or hierarchically ordered outcomes.
19. Consistency and inconsistency in $k$-means clustering
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2507.06226
   A celebrated result of Pollard proves asymptotic consistency for $k$-means clustering when the population distribution has finite variance.
20. Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.13305
   Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to regularisation choices.
21. Pathwise skew-symmetric discretisation for SDEs with superlinear drift
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2607.17735
   The skew-symmetric discretisation has recently been proposed as a new robust simulation method for weakly approximating stochastic differential equations (SDEs) with non-globally Lipschitz drift.
22. High-dimensional networks and mean squared error for possibly misspecified models
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.13171
   To avoid missing important variables and their connections in networks, more and more variables are included in network analysis.
23. Random Inverse Problems with Structural and Probabilistic Ambiguities
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2608.01439
   In this paper, we investigate a computational class of random inverse problems that incorporates model uncertainties through random variable parameters nonlinearly in the forward model as well as additive observational uncertainty.
24. The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2608.13520
   We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}).
25. A Metric Space of Spatial Graphs: Two-Sample Testing, Data Depth, and Application to Cardiac Fibrosis
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.13406
   Cardiac fibrosis reduces electrical conductivity and is a leading cause of arrhythmia.
26. Change point analysis of high-dimensional data using random projections
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2602.19988
   This paper develops a novel change point identification method for high-dimensional data using random projections.
27. Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.13418
   Given a dataset where a portion of the samples are contaminated, our goal is to recover the underlying clean population distribution.
28. Cohen's f or Mean Standardized Differences? Assessing Covariate Balance with Multivalued Treatments
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2608.10266
   Assessing covariate balance across more than two treatment groups has no established omnibus standard: the prevailing practice averages, or takes the maximum of, pairwise standardized mean differences (SMD), while Cohen's f - the classical generalization of Cohen's d to more than two groups - offers an alternative grounded in an established effect-size framework, but the two have not been formally compared.
29. Theoretical Properties of Covariate-Adaptive Randomization with a Diverging Number of Covariates
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2608.13442
   Covariate-adaptive randomization procedures are widely used in clinical trials to improve covariate balance.
30. Predicting consumer-technology ownership without a diffusion history
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2608.12344
   We test whether the perceived attributes of a consumer technology predict how widely it is owned.
31. R\'enyi's $\alpha$-divergence variational Bayes for spike-and-slab high-dimensional linear regression
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2512.00627
   Sparse high-dimensional linear regression is a central problem in statistics, where the goal is often variable selection and/or coefficient estimation.
32. Bagging Robustly Learns VC Classes with Linear Sample Complexity
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2608.13514
   We revisit the problem of learning predictors robust to adversarial examples at test-time.

Sources in this brief: stat.AP (Applications); stat.CO (Computation); stat.ME (Methodology); stat.ML (Machine Learning); stat.OT (Other Statistics); stat.TH (Statistics Theory).
Selected 32 of 435 available items for this weekly brief.