ArXiv Paperboy (Stat.ME+Econ.EM)

Canonical Polyadic (CP) tensor decomposition is a fundamental technique for analyzing high-dimensional tensor data. While the Alternating Least Squares (ALS) algorithm is widely used for computing CP decomposition due to its simplicity and empirical success, its theoretical foundation, particularly regarding statistical optimality and convergence behavior, remain underdeveloped, especially in noisy, non-orthogonal, and higher-rank settings. In this work, we revisit CP tensor decomposition from a statistical perspective and provide a comprehensive theoretical analysis of ALS under a signal-plus-noise model. We establish non-asymptotic, minimax-optimal error bounds for tensors of general order, dimensions, and rank, assuming suitable initialization. To enable such initialization, we propose Tucker-based Approximation with Simultaneous Diagonalization (TASD), a robust method that improves stability and accuracy in noisy regimes. Combined with ALS, TASD yields a statistically consistent estimator. We further analyze the convergence dynamics of ALS, identifying a two-phase pattern-initial quadratic convergence followed by linear refinement. We further show that in the rank-one setting, ALS with an appropriately chosen initialization attains optimal error within just one or two iterations.

arXiv📈🤖
Revisit CP Tensor Decomposition: Statistical Optimality and Fast Convergence
By Tang, Chhor, Klopp et al

arXiv:2202.13000v2 Announce Type: replace Abstract: In this paper, we consider robust estimation of claim severity models in insurance, when data are affected by truncation (due to deductibles), censoring (due to policy limits), and scaling (due to coinsurance). In particular, robust estimators based on the methods of trimmed moments (T-estimators) and winsorized moments (W-estimators) are pursued and fully developed. The general definitions of such estimators are formulated and their asymptotic properties are investigated. For illustrative purposes, specific formulas for T- and W-estimators of the tail parameter of a single-parameter Pareto distribution are derived. The practical performance of these estimators is then explored using the well-known Norwegian fire claims data. Our results demonstrate that T- and W-estimators offer a robust and computationally efficient alternative to the likelihood-based inference for models that are affected by deductibles, policy limits, and coinsurance.

arXiv📈🤖
Robust Estimation of Loss Models for Truncated and Censored Severity Data
By

arXiv:2402.11341v1 Announce Type: new Abstract: Clustered data are common in practice. Clustering arises when subjects are measured repeatedly, or subjects are nested in groups (e.g., households, schools). It is often of interest to evaluate the correlation between two variables with clustered data. There are three commonly used Pearson correlation coefficients (total, between-, and within-cluster), which together provide an enriched perspective of the correlation. However, these Pearson correlation coefficients are sensitive to extreme values and skewed distributions. They also depend on the scale of the data and are not applicable to ordered categorical data. Current non-parametric measures for clustered data are only for the total correlation. Here we define population parameters for the between- and within-cluster Spearman rank correlations. The definitions are natural extensions of the Pearson between- and within-cluster correlations to the rank scale. We show that the total Spearman rank correlation approximates a weighted sum of the between- and within-cluster Spearman rank correlations, where the weights are functions of rank intraclass correlations of the two random variables. We also discuss the equivalence between the within-cluster Spearman rank correlation and the covariate-adjusted partial Spearman rank correlation. Furthermore, we describe estimation and inference for the three Spearman rank correlations, conduct simulations to evaluate the performance of our estimators, and illustrate their use with data from a longitudinal biomarker study and a clustered randomized trial.

arXiv📈🤖
Between- and Within-Cluster Spearman Rank Correlations
By

arXiv:2404.06093v1 Announce Type: new Abstract: The contamination detection problem aims to determine whether a set of observations has been contaminated, i.e. whether it contains points drawn from a distribution different from the reference distribution. Here, we consider a supervised problem, where labeled samples drawn from both the reference distribution and the contamination distribution are available at training time. This problem is motivated by the detection of rare cells in flow cytometry. Compared to novelty detection problems or two-sample testing, where only samples from the reference distribution are available, the challenge lies in efficiently leveraging the observations from the contamination detection to design more powerful tests. In this article, we introduce a test for the supervised contamination detection problem. We provide non-asymptotic guarantees on its Type I error, and characterize its detection rate. The test relies on estimating reference and contamination densities using histograms, and its power depends strongly on the choice of the corresponding partition. We present an algorithm for judiciously choosing the partition that results in a powerful test. Simulations illustrate the good empirical performances of our partition selection algorithm and the efficiency of our test. Finally, we showcase our method and apply it to a real flow cytometry dataset.

arXiv📈🤖
Supervised Contamination Detection, with Flow Cytometry Application
By

The m-out-of-n bootstrap is a possible workaround to compute confidence intervals for bootstrap inconsistent estimators, because it works under weaker conditions than the n-out-of-n bootstrap. It has the disadvantage, however, that it requires knowledge of an appropriate scaling factor {\tau}n and that the coverage probability for finite n depends on the choice of m. This article presents an R package moonboot which implements the computation of m-out-of-n bootstrap confidence intervals and provides functions for estimating the parameters {\tau}n and m. By means of Monte Carlo simulations, we evaluate the different methods and compare them for different estimators

arXiv📈🤖
moonboot: An R Package Implementing m-out-of-n Bootstrap Methods
By Dalitz, L\"ogler

The 2023 U.S. banking crisis propagated not through direct financial linkages but through a high-frequency, information-based contagion channel. This paper moves beyond exploration analysis to test the "too-similar-to-fail" hypothesis, arguing that risk spillovers were driven by perceived similarities in bank business models under acute interest rate pressure. Employing a Time-Varying Parameter Vector Autoregression (TVP-VAR) model with 30-day rolling windows, a method uniquely suited for capturing the rapid network shifts inherent in a panic, we analyze daily stock returns for the four failed institutions and a systematically selected peer group of surviving banks vulnerable to the same risks from March 18, 2022, to March 15, 2023. Our results provide strong evidence for this contagion channel: total system connectedness surged dramatically during the crisis peak, and we identify SIVB, FRC, and WAL as primary net transmitters of risk while their perceived peers became significant net receivers, a key dynamic indicator of systemic vulnerability that cannot be captured by asset-by-asset analysis. We further demonstrate that these spillovers were significantly amplified by market sentiment (as measured by the VIX) and economic policy uncertainty (EPU). By providing a clear conceptual framework and robust empirical validation, our findings confirm the persistence of systemic risks within the banking network and highlight the importance of real-time monitoring in strengthening financial stability.

arXiv📈🤖
Dynamic Risk in the U.S. Banking System: An Analysis of Sentiment, Policy Shocks, and Spillover Effects
By Wang, Huang, Sua et al

Rising CO$_2$ emissions remain a critical global challenge, particularly in middle-income countries where economic growth drives environmental degradation. This study examines the long-run and short-run relationships between CO$_2$ emissions, energy use, GDP per capita, and population across 106 middle-income countries from 1980 to 2023. Using a Panel Vector Error Correction Model (VECM), we assess the impact of the Paris Agreement (2015) on emissions while conducting cointegration tests to confirm long-run equilibrium relationships. The findings reveal a strong long-run relationship among the variables, with energy use as the dominant driver of emissions, while GDP per capita has a moderate impact. However, the Paris Agreement has not significantly altered emissions trends in middle-income economies. Granger causality tests indicate that energy use strongly causes emissions, but GDP per capita and population do not exhibit significant short-run causal effects. Variance decomposition confirms that energy shocks have the most persistent effects, and impulse response functions (IRFs) show emissions trajectories are primarily shaped by economic activity rather than climate agreements. Robustness checks, including autocorrelation tests, polynomial root stability, and Yamagata-Pesaran slope homogeneity tests, validate model consistency. These results suggest that while global agreements set emissions reduction goals, their effectiveness remains limited without stronger national climate policies, sectoral energy reforms, and financial incentives for clean energy adoption to ensure sustainable economic growth.

arXiv📈🤖
Has the Paris Agreement Shaped Emission Trends? A Panel VECM Analysis of Energy, Growth, and CO$_2$ in 106 Middle-Income Countries
By Mamun, Ehsanullah

Extremile regression, as a least squares analog of quantile regression, is potentially useful tool for modeling and understanding the extreme tails of a distribution. However, existing extremile regression methods, as nonparametric approaches, may face challenges in high-dimensional settings due to data sparsity, computational inefficiency, and the risk of overfitting. While linear regression serves as the foundation for many other statistical and machine learning models due to its simplicity, interpretability, and relatively easy implementation, particularly in high-dimensional settings, this paper introduces a novel definition of linear extremile regression along with an accompanying estimation methodology. The regression coefficient estimators of this method achieve $\sqrt{n}$-consistency, which nonparametric extremile regression may not provide. In particular, while semi-supervised learning can leverage unlabeled data to make more accurate predictions and avoid overfitting to small labeled datasets in high-dimensional spaces, we propose a semi-supervised learning approach to enhance estimation efficiency, even when the specified linear extremile regression model may be misspecified. Both simulation studies and real data analyses demonstrate the finite-sample performance of our proposed methods.

arXiv📈🤖
Semi-supervised learning for linear extremile regression
By Jiang, Yu, Wang

arXiv:2406.08022v1 Announce Type: new Abstract: Bayes factor null hypothesis tests provide a viable alternative to frequentist measures of evidence quantification. Bayes factors for realistic interesting models cannot be calculated exactly, but have to be estimated, which involves approximations to complex integrals. Crucially, the accuracy of these estimates, i.e., whether an estimated Bayes factor corresponds to the true Bayes factor, is unknown, and may depend on data, prior, and likelihood. We have recently developed a novel statistical procedure, namely simulation-based calibration (SBC) for Bayes factors, to test for a given analysis, whether the computed Bayes factors are accurate. Here, we use SBC for Bayes factors to test for some common cognitive designs, whether Bayes factors are estimated accurately. We use the bridgesampling/brms packages as well as the BayesFactor package in R. We find that Bayes factor estimates are accurate and exhibit only little bias in Latin square designs with (a) random effects for subjects only and (b) for crossed random effects for subjects and items, but a single fixed-factor. However, Bayes factor estimates turn out biased and liberal in a 2x2 design with crossed random effects for subjects and items. These results suggest that researchers should test for their individual analysis, whether Bayes factor estimates are accurate. Moreover, future research is needed to determine the boundary conditions under which Bayes factor estimates are accurate or biased, as well as software development to improve estimation accuracy.

arXiv📈🤖
Null hypothesis Bayes factor estimates can be biased in (some) common factorial designs: A simulation study
By

Causal structure learning from observational data is central to many scientific and policy domains, but the time series setting common to many disciplines poses several challenges due to temporal dependence. In this paper we focus on score-based causal discovery for multivariate time series and introduce TS-BOSS, a time series extension of the recently proposed Best Order Score Search (BOSS) (Andrews et al. 2023). TS-BOSS performs a permutation-based search over dynamic Bayesian network structures while leveraging grow-shrink trees to cache intermediate score computations, preserving the scalability and strong empirical performance of BOSS in the static setting. We provide theoretical guarantees establishing the soundness of TS-BOSS under suitable assumptions, and we present an intermediate result that extends classical subgraph minimality results for permutation-based methods to the dynamic (time series) setting. Our experiments on synthetic data show that TS-BOSS is especially effective in high auto-correlation regimes, where it consistently achieves higher adjacency recall at comparable precision than standard constraint-based methods. Overall, TS-BOSS offers a high-performing, scalable approach for time series causal discovery and our results provide a principled bridge for extending sparsity-based, permutation-driven causal learning theory to dynamic settings.

arXiv📈🤖
Learning Causal Structure of Time Series using Best Order Score Search
By Mansilla, Ninad

When multiple datasets describe complementary information about the same set of entities, for example, brain scans of an individual over time, global trade network across years, or user information across social media platforms, integrating these snapshots allows us to see a more holistic picture. A common way of identifying structure in data is through clustering, but while clustering may be applied to each dataset separately, we learn more in the multi-view setting by identifying joint clusters. We consider a clustering problem where each view conflates some of these joint clusters, only revealing partial information, and seek to recover the true joint cluster structure. We introduce this multi-view clustering model and a method for recovering it: the transposed Khatri-RAo Framework for joinT cluster recoverY (KRAFTY). The model is flexible and can accommodate a variety of data-generating processes, including latent positions in random dot product graphs and Gaussian mixtures. A key advantage of KRAFTY is that it represents joint clusters in a space with sufficient dimension so that each joint cluster occupies an orthogonal subspace in the transposed Khatri-Rao matrix, which results in a sharp drop in the scree plot at the true number of joint clusters, enabling easy model selection. Our simulations show that when the number of joint clusters exceeds the sum of the numbers of clusters in each individual view, our method outperforms existing methods in both joint clustering accuracy and estimation of the number of joint clusters.

arXiv📈🤖
KRAFTY: Khatri-Rao Framework for Joint Cluster Recovery
By Gao, Lubberts, Pensky

Most statistical process monitoring methods for multichannel profiles focus solely on the mean and are almost ineffective when changes involve the covariance structure. Although it is known to be crucial, covariance monitoring requires estimating a much larger number of parameters, which may shift in a subtle and sparse fashion. That is, an out-of-control (OC) state may manifest with small deviations and affect only a very limited subset of these parameters. To address these difficulties, we propose a multichannel profile covariance (MPC) control chart based on functional graphical models that provide an interpretable representation of conditional dependencies between profiles. A nonparametric combination of the likelihood-ratio tests corresponding to different sparsity levels is then used to draw an overall inference and signal whether an OC state may have occurred. Between-profile relationships that are likely to have shifted are naturally identified at no additional computational cost. An extensive Monte Carlo simulation study compares the MPC control chart with state-of-the-art competitors, and a case study on monitoring multichannel temperature profiles in a roasting machine illustrates its practical applicability.

arXiv📈🤖
Monitoring Covariance in Multichannel Profiles via Functional Graphical Models
By Capezza, Forcina, Lepore et al

Modern data analysis across diverse disciplines increasingly relies on time series. Many of these datasets exhibit cyclostationarity, where patterns approximately repeat in a regular manner, often across multiple time scales, such as daily, weekly or yearly cycles. In this context, statistical inference is essential to distinguish genuine underlying effects from random variability. While tools like Analysis of Variance (ANOVA) provide such inference, they often lack interpretability and struggle with the complexities of multivariate data. To address these limitations, we propose a unified pipeline for the exploratory analysis of cyclostationary times series using ANOVA Simultaneous Component Analysis (ASCA). ASCA is an extension of ANOVA that is able to work in both univariate and multivariate cases. Combining inference with the visualization capabilities of Principal Component Analysis (PCA), ASCA provides powerful options for interpretability. ASCA's capabilities have been well-established in the analysis of experimental data, but they remain largely unexplored for observational data like time series. Our workflow introduces an algorithmic approach to modeling time-dependent data using ASCA, enabling control over multiple cyclostationary time scales while also accounting for the specific challenges of this type of data, such as autocorrelation. Furthermore, we observed that ASCA provides a better separation of variability across factors than ANOVA in unbalanced designs due to its multivariate nature. We demonstrate the efficacy of this methodology through two real-world case studies: water temperature trends in mountain lakes in Sierra Nevada, Spain, and airborne pollen trends over 30 years recorded in the city of Granada, Spain.

arXiv📈🤖
Modeling cyclostationarity in time series using ASCA
By Vallejo-Espa\~na, S\'anchez, Villar-Argaiz et al

Structural break identification methods are an important tool for evaluating the effectiveness of climate change mitigation policies. In this paper, we introduce a unified probabilistic framework for detecting structural breaks with unknown timing and arbitrary sequence in longitudinal data. The proposed Bayesian setup uses indicator-saturated regression and a spike-and-slab prior with an inverse-moment density as the slab component to ensure model selection consistency. Simulation results show that the method outperforms comparable frequentist approaches, particularly in environments with a high probability of structural breaks. We apply the framework to identify and evaluate the effects of climate policies in the European road transport sector.

arXiv📈🤖
Bayesian Indicator-Saturated Regression for Climate Policy Evaluation
By Konrad, Vashold, Cuaresma

This paper deals with the problem of outliers in high frequency observation data from diffusion processes. Robust estimation methods are needed because the inclusion of outliers can lead to incorrect statistical inference even in the diffusion process. To construct a robust estimator, we first approximate the transition density of the diffusion process to the Gaussian density by using Kessler's approach and then employ two types of minimum robust divergence estimation methods. In this paper, we provide the asymptotic properties of the robust estimator using $\gamma$-divergence. Furthermore, we derive the conditional influence functions of the estimation using divergences and discuss its boundness.

arXiv📈🤖
Robust estimation via $\gamma$-divergence for diffusion processes
By Nakagawa, Shimizu

Numerical models are widely used to simulate the earth system, but they are computationally expensive and often depend on many uncertain input parameters. Their effective use requires calibration and uncertainty quantification, which typically involve running the model across many input configurations and therefore incur substantial computational cost. Statistical emulation provides a practical alternative for efficiently exploring model behavior. We are motivated by the Arctic sea ice component of the Energy Exascale Earth System Model (MPAS-Seaice), which generates large spatiotemporal outputs at multiple spatial resolutions, with high-resolution (or high-fidelity, HF) simulations being more accurate but computationally more expensive than lower-resolution (low-fidelity, LF) simulations. Multi-fidelity (MF) emulation integrates information across resolutions to construct efficient and accurate surrogate models, yet existing approaches struggle to scale to large spatiotemporal data. We develop an MF emulator that combines tensor decomposition for dimensionality reduction, Gaussian process priors for flexible function approximation, and an additive discrepancy model to capture systematic differences between LF and HF data. The proposed framework enables scalable emulation while maintaining accurate predictions and well-calibrated uncertainty for complex spatiotemporal fields, and consistently achieves lower prediction error and reduced uncertainty than LF-only and HF-only models in both simulation studies and MPAS-Seaice analysis. By leveraging the complementary strengths of LF and HF data and using an efficient tensor decomposition approach, our emulator greatly reduces computational expense, making it well suited for large-scale simulation tasks involving complex physical models.

arXiv📈🤖
A Multi-Fidelity Tensor Emulator for Spatiotemporal Outputs: Emulation of Arctic Sea Ice Dynamics
By Contant, Guan, Wilson et al

Regression is the workhorse of statistics, and is often faced with real data that contain outliers. When these are casewise outliers, that is, cases that are entirely wrong or belong to a different population, the issue can be remedied by existing casewise robust regression methods. It is another matter when cellwise outliers occur, that is, suspicious individual entries in the data matrix containing the regressors and the response. We propose a new regression method that is robust to both casewise and cellwise outliers, and handles missing values as well. Its construction allows for skewed distributions. We show that it obeys the first breakdown result for cellwise robust regression. It is also the first such method that is geared to making robust out-of-sample predictions. Its performance is studied by simulation, and it is illustrated on a substantial real dataset.

arXiv📈🤖
Least trimmed squares regression with missing values and cellwise outliers
By Raymaekers, Rousseeuw

Survey sampling is concerned with the estimation of finite population parameters. In practice, survey data suffer from item nonresponse, which is commonly handled through imputation, i.e., replacing missing values with predicted values. As a result, the properties of the resulting imputed estimator depend critically on the properties of the prediction method used. In turn, prediction methods themselves depend on the choice of variables and tuning parameters used to fit the imputation model. In this article, we study the problem of variable selection for linear regression imputation. Although variable selection has been widely studied across many fields, primarily for identification or prediction, its role in imputation for survey data has received comparatively little attention. We introduce the notion of an optimal imputation model defined through an oracle loss function and show that, with probability tending to one, the optimal model coincides with the true model. We also examine the consequences of using misspecified models -- either omitting relevant covariates or including irrelevant ones -- on consistency and asymptotic variance. We then develop a complete methodological framework for constructing confidence intervals after model selection. The proposed confidence intervals are shown to be asymptotically valid and optimal among all candidate models. Simulation studies indicate that the proposed methodology performs well in finite samples.

arXiv📈🤖
Variable Selection for Linear Regression Imputation in Surveys
By An, Dagdoug, Haziza

With the advent of effective pre-exposure prophylaxis agents, active-controlled HIV prevention trials have become a common study design. Nevertheless, estimating absolute efficacy relative to a placebo remains important. In this paper, we introduce a novel application of proximal causal inference methods to estimate the counterfactual cumulative HIV incidence under placebo for participants in an active-controlled trial of cabotegravir, using external control data from a placebo-controlled trial with similar eligibility criteria. We leverage baseline sexually transmitted infection status and geographic region as negative control outcome and exposure variables, respectively. We address two key challenges: unmeasured differences in HIV risk between trials and statistical difficulties arising from low HIV incidence rates in both studies. To overcome these challenges, we develop two proximal inference approaches: (1) a semiparametric inverse probability of censoring weighting estimator, and (2) a two-stage regression-based strategy tailored to low-event-rate settings. Our theoretical and numerical investigations demonstrate these methods yield reliable estimates of the counterfactual one-year cumulative HIV incidence under placebo, and provide robust evidence of the superior efficacy of cabotegravir compared with placebo. These findings highlight the potential of proximal inference methods to estimate placebo-controlled effects in both single-arm and active-controlled trials by leveraging external controls.

arXiv📈🤖
Proximal Learning for Trials With External Controls: A Case Study in HIV Prevention
By Song, Wu, Landovitz et al

In this paper, we introduce a novel method for constructing probability distributions on the unit interval by exploiting the non-injective transformation defined by the ratio of two positive random variables, $X$ and $Y$. For simplicity and tractability, we focus on independent random variables $X$ and $Y$ following gamma distributions. We derive some results including laws, density functions, quantile function and closed-form expressions for the moments, and discuss maximum likelihood estimation.

arXiv📈🤖
Constructing new probability distributions on the unit interval
By Vila, Saulo, Matos et al

This paper develops a general asymptotic theory of series ridge estimators for spatial data observed at irregularly spaced locations in a sampling region $R_n \subset \mathbb{R}^d$. We adopt a stochastic sampling design that can generate irregularly spaced sampling sites in a flexible manner including both pure increasing and mixed increasing domain frameworks. Specifically, we consider a spatial trend regression model and a nonparametric regression model with spatially dependent covariates. For these models, we investigate the $L^2$-penalized series estimation of the trend and regression functions and establish (i) uniform and $L^2$ convergence rates and (ii) multivariate central limit theorems for general series estimators, (iii) optimal uniform and $L^2$ convergence rates for spline and wavelet series estimators, and (iv) show that our dependence structure conditions on the underlying spatial processes cover a wide class of random fields including L\'evy-driven continuous autoregressive and moving average random fields.

arXiv📈🤖
Series ridge regression for spatial data on $\mathbb{R}^d$
By

Small sample sizes in clinical studies arises from factors such as reduced costs, limited subject availability, and the rarity of studied conditions. This creates challenges for accurately calculating confidence intervals (CIs) using the normal distribution approximation. In this paper, we employ a quadratic-form based statistic, from which we derive more accurate confidence intervals, particularly for data with small sample sizes or proportions. Based on the study, we suggest reasonable values of sample sizes and proportions for the application of the quadratic method. Consequently, this method enhances the reliability of statistical inferences. We illustrate this method with real medical data from clinical trials.

arXiv📈🤖
Confidence Intervals Based on the Modified Chi-Squared Distribution and its Applications in Medicine
By Wu, Xu, Kim

arXiv:2406.11940v1 Announce Type: new Abstract: The stable unit treatment value assumption states that the outcome of an individual is not affected by the treatment statuses of others, however in many real world applications, treatments can have an effect on many others beyond the immediately treated. Interference can generically be thought of as mediated through some network structure. In many empirically relevant situations however, complete network data (required to adjust for these spillover effects) are too costly or logistically infeasible to collect. Partially or indirectly observed network data (e.g., subsamples, aggregated relational data (ARD), egocentric sampling, or respondent-driven sampling) reduce the logistical and financial burden of collecting network data, but the statistical properties of treatment effect adjustments from these design strategies are only beginning to be explored. In this paper, we present a framework for the estimation and inference of treatment effect adjustments using partial network data through the lens of structural causal models. We also illustrate procedures to assign treatments using only partial network data, with the goal of either minimizing estimator variance or optimally seeding. We derive single network asymptotic results applicable to a variety of choices for an underlying graph model. We validate our approach using simulated experiments on observed graphs with applications to information diffusion in India and Malawi.

arXiv📈🤖
Model-Based Inference and Experimental Design for Interference Using Partial Network Data
By

We study the deployment performance of machine learning based enforcement systems used in cryptocurrency anti money laundering (AML). Using forward looking and rolling evaluations on Bitcoin transaction data, we show that strong static classification metrics substantially overstate real world regulatory effectiveness. Temporal nonstationarity induces pronounced instability in cost sensitive enforcement thresholds, generating large and persistent excess regulatory losses relative to dynamically optimal benchmarks. The core failure arises from miscalibration of decision rules rather than from declining predictive accuracy per se. These findings underscore the fragility of fixed AML enforcement policies in evolving digital asset markets and motivate loss-based evaluation frameworks for regulatory oversight.

arXiv📈🤖
Algorithmic Compliance and Regulatory Loss in Digital Assets
By Bhatt, Sharma

Large language models (LLMs) are trained on enormous amounts of data and encode knowledge in their parameters. We propose a pipeline to elicit causal relationships from LLMs. Specifically, (i) we sample many documents from LLMs on a given topic, (ii) we extract an event list from from each document, (iii) we group events that appear across documents into canonical events, (iv) we construct a binary indicator vector for each document over canonical events, and (v) we estimate candidate causal graphs using causal discovery methods. Our approach does not guarantee real-world causality. Rather, it provides a framework for presenting the set of causal hypotheses that LLMs can plausibly assume, as an inspectable set of variables and candidate graphs.

arXiv📈🤖
Causality Elicitation from Large Language Models
By Kameyama, Kato, Hio et al

Experimentation is central to modern digital businesses, but many operational decisions cannot be randomized at the user level. In such cases, cluster-level experiments, where clusters are usually geographic, come to the rescue. However, such experiments often suffer from low power due to persistent cluster heterogeneity, strong seasonality, and autocorrelated outcome metrics, as well as common shocks that move many clusters simultaneously. On an example of airline pricing - where policies are typically applied at the route level and thus the A/B test unit of analysis is a route - we study switchback designs to remedy these problems. In switchback designs, each cluster (route in our case) alternates between treatment and control on a fixed schedule, creating within-route contrasts that mitigate time-invariant heterogeneity and reduce sensitivity to low-frequency noise. We provide a unified Two-Way Fixed Effects interpretation of switchback experiments that makes the identifying variation explicit after partialling out route and time effects, clarifying how switching cadence interacts with temporal dependence to determine precision. Empirically, we evaluate weekly and daily switchback cadences using calibrated synthetic regimes and operational airline data from ancillary pricing. In our evaluations, switchbacks decrease standard errors by up to 67%, with daily switching yielding the largest gains over short horizons and weekly switching offering a strong and simpler-to-operationalize alternative.

arXiv📈🤖
Cluster-Level Experiments using Temporal Switchback Designs: Precision Gains in Pricing A/B Tests at LATAM Airlines
By Ferrari-Ortiz, Orellana-Montini, Abbiasov et al

Density aggregation is a central problem in machine learning, for instance when combining predictions from a Deep Ensemble. The choice of aggregation remains an open question with two commonly proposed approaches being linear pooling (probability averaging) and geometric pooling (logit averaging). In this work, we address this question by studying the normalized generalized mean of order $r \in \mathbb{R} \cup \{-\infty,+\infty\}$ through the lens of log-likelihood, the standard evaluation criterion in machine learning. This provides a unifying aggregation formalism and shows different optimal configurations for different situations. We show that the regime $r \in [0,1]$ is the only range ensuring systematic improvements relative to individual distributions, thereby providing a principled justification for the reliability and widespread practical use of linear ($r=1$) and geometric ($r=0$) pooling. In contrast, we show that aggregation rules with $r \notin [0,1]$ may fail to provide consistent gains with explicit counterexamples. Finally, we corroborate our theoretical findings with empirical evaluations using Deep Ensembles on image and text classification benchmarks.

arXiv📈🤖
Beyond Mixtures and Products for Ensemble Aggregation: A Likelihood Perspective on Generalized Means
By Razafindralambo, Sun, Precioso et al

Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphasis and aims. This work introduces a new quantitative notion of privacy that is both contextual and specific. We argue that it provides a more meaningful notion of privacy than the widely utilised framework of differential privacy and a more explicit and rigorous formulation than what is commonly used in statistical disclosure theory. Our definition relies on concepts inherent to standard Bayesian decision theory, while departing from it in several important respects. In particular, the party controlling the release of sensitive information should make disclosure decisions from the prior viewpoint, rather than conditional on the data, even when the data is itself observed. Illuminating toy examples and computational methods are discussed in high detail in order to highlight the specificities of the method.

arXiv📈🤖
Bayesian Adversarial Privacy
By Bell, Johnston, Luciano et al

The Bayesian and Akaike information criteria aim at finding a good balance between under- and over-fitting. They are extensively used every day by practitioners. Yet we contend they suffer from at least two afflictions: their penalty parameter $\lambda=\log n$ and $\lambda=2$ are too small, leading to many false discoveries, and their inherent (best subset) discrete optimization is infeasible in high dimension. We alleviate these issues with the pivotal information criterion: PIC is defined as a continuous optimization problem, and the PIC penalty parameter $\lambda$ is selected at the detection boundary (under pure noise). PIC's choice of $\lambda$ is the quantile of a statistic that we prove to be (asymptotically) pivotal, provided the loss function is appropriately transformed. As a result, simulations show a phase transition in the probability of exact support recovery with PIC, a phenomenon studied with no noise in compressed sensing. Applied on real data, for similar predictive performances, PIC selects the least complex model among state-of-the-art learners.

arXiv📈🤖
The Pivotal Information Criterion
By Sardy, Cutsem, Geer

The growing use of unstructured text in business research makes topic modeling a central tool for constructing explanatory variables from reviews, social media, and open-ended survey responses, yet existing approaches function poorly as measurement instruments. Prior work shows that textual content predicts outcomes such as sales, satisfaction, and firm performance, but probabilistic models often generate conceptually diffuse topics, neural topic models are difficult to interpret in theory-driven settings, and large language model approaches lack standardization, stability, and alignment with document-level representations. We introduce LX Topic, a neural topic method that conceptualizes topics as latent linguistic constructs and produces calibrated document-level topic proportions for empirical analysis. LX Topic builds on FASTopic to ensure strong document representativeness and integrates large language model refinement at the topic-word level using alignment and confidence-weighting mechanisms that enhance semantic coherence without distorting document-topic distributions. Evaluations on large-scale Amazon and Yelp review datasets demonstrate that LX Topic achieves the highest overall topic quality relative to leading models while preserving clustering and classification performance. By unifying topic discovery, refinement, and standardized output in a web-based system, LX Topic establishes topic modeling as a reproducible, interpretable, and measurement-oriented instrument for marketing research and practice.

arXiv📈🤖
A Neural Topic Method Using a Large-Language-Model-in-the-Loop for Business Research
By Ludwig, Danaher, Yang