Clay weekly context brief for the Statistics category (ISO week 2026-W28).

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. Partial Causal Structure Learning for Valid Selective Conformal Inference under Interventions
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2603.02204
   Selective conformal prediction can yield substantially tighter uncertainty sets when we can identify calibration examples that are exchangeable with the test example.
2. Multi-Distribution Robust Conformal Prediction
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2601.02998
   In many fairness and distribution robustness problems, one has access to labeled data from multiple source distributions yet the test data may come from an arbitrary member or a mixture of them.
3. Walk on spheres and Array-RQMC
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2605.12844
   We use Array-RQMC sampling in a walk on spheres (WoS) algorithm for Dirichlet boundary value problems.
4. The Proxy Presumption: From Semantic Embeddings to Valid Social Measures
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2605.07409
   Natural Language Processing is rapidly evolving into a primary instrument for Computational Social Science, with researchers increasingly using embeddings to measure latent constructs such as novelty, creativity, and bias.
5. Conditional Mean Independence and Global Sensitivity Analysis using Nearest Neighbor Graphs
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2607.04692
   Quantifying how well a conditional mean function explains a response is central to many statistical tasks, such as model evaluation and feature screening.
6. Quantum Circuit Generation via test-time learning with large language models
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2602.03466
   Deploying large language models (LLMs) as optimizers for black-box scientific design problems requires efficient test-time refinement under expensive evaluations and without training data.
7. Testing the equality of estimable parameters
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2607.07588
   This paper proposes a general and unified framework for testing the equality of a broad class of parameters, defined via $U$-statistics, across multiple independent populations.
8. Rotated Mean-Field Variational Inference and Iterative Gaussianization
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2510.07732
   We propose an iterative Gaussianization method for sampling from unnormalized densities by repeatedly applying mean-field variational inference (MFVI) in rotated coordinate systems.
9. Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Model Sharing
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2602.18396
   We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a communication-efficient Byzantine-robust federated conformal prediction framework that uses partial model sharing to mitigate stochastic model-poisoning attacks during training and histogram-based filtering to mitigate adversarial calibration submissions.
10. Sub-Gaussian Concentration and Entropic Normality of the Maximum Likelihood Estimator
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2605.07107
   It is well known that, under standard regularity conditions, the maximum likelihood estimator (MLE) satisfies a central limit theorem and converges in distribution to a Gaussian random variable as the sample size grows.
11. Geometry-Aware Deep Congruence Networks for Manifold Learning in Cross-Subject Motor Imagery
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2511.18940
   Cross-subject motor imagery decoding remains a fundamental challenge in EEG-based brain-computer interfaces due to substantial inter-subject variability.
12. Robust Indicators of Spatial Association
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2607.07215
   The Moran statistic, and its accompanying local statistics, are one of the most extensively used exploratory spatial data analysis tools for assessing global and local spatial autocorrelation.
13. weightflow: declarative, recipe-aware survey weighting in R
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2607.08491
   Producing analysis weights for a complex survey requires a sequence of hierarchical adjustments (resolving unknown eligibility, dropping out-of-scope units, restoring within-household selection, correcting for nonresponse, and calibrating to known population totals), after which design-consistent variances must account for the fact that several adjustments were themselves estimated from the sample.
14. Low-Turnover Rebalancing for Sparse Index Tracking
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2512.22109
   Sparse index tracking is often evaluated through rolling reconstruction: a sparse portfolio is fitted on an in-sample window, held over the next period, and rebuilt when the window rolls forward.
15. Maximum Mean Discrepancy with Unequal Sample Sizes via Generalized U-Statistics
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2512.13997
   Existing two-sample testing techniques, particularly those based on choosing a kernel for the Maximum Mean Discrepancy (MMD), often assume equal sample sizes from the two distributions.
16. On the Gradient Complexity of Private Optimization with Private Oracles
   Source: stat.ML (Machine Learning)
   Link: https://arxiv.org/abs/2511.13999
   We study the running time, in terms of first order oracle queries, of differentially private empirical/population risk minimization of Lipschitz convex losses.
17. Beyond Laplace: Closed-form wrapped Gaussian posterior approximations on statistical manifolds
   Source: stat.ME (Methodology)
   Link: https://arxiv.org/abs/2607.01909
   In Bayesian statistics, the Laplace approximation provides a computationally efficient approximation to posterior distributions.
18. A scalable version of MADD for big-data classification
   Source: stat.CO (Computation)
   Link: https://arxiv.org/abs/2607.08334
   Distance-based classifiers are very popular, and the Euclidean distance is one of the most commonly used metrics in distance-based classifiers.
19. Enhancing the KidSat Model: Integrating Geographical Encoding and Data Quality Assessment for Childhood Poverty Prediction
   Source: stat.AP (Applications)
   Link: https://arxiv.org/abs/2607.08281
   Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as cloud cover and image corruption, and (iii) lack of explicit spatial structure in image-only models.
20. On the optimal prediction of extreme events
   Source: stat.TH (Statistics Theory)
   Link: https://arxiv.org/abs/2606.26270
   The prediction of the extremely large values of a response variable $Y$ in terms of a vector of covariates $X=(X_i)_{i=1}^d$ is a fundamental problem arising in many scientific and engineering domains.

Sources in this brief: stat.AP (Applications); stat.CO (Computation); stat.ME (Methodology); stat.ML (Machine Learning); stat.TH (Statistics Theory).
Selected 20 of 71 available items for this weekly brief.