427 papers
This paper introduces a cosmology-inspired reliability framework that employs deterministic perturbation bounds and multi-level admission gates to certify the accuracy of spectral clustering on graph Laplacians, demonstrating that directional certificates and amplitude-uniform gates outperform scalar residuals in validating eigenvector stability under discrete noise.
This paper proposes a Semi-Berry approximation that partitions scale-homogeneous random variables into Gaussian-aggregated and simulation-targeted groups based on the Lyapunov ratio, significantly reducing tail quantile errors and computational costs compared to standard Normal approximations or full Monte Carlo simulations.
This paper proposes a robust bootstrap test for bidirectional Granger causality in Gaussian VAR models that utilizes unexplained mutual information, an intersection-union procedure, and Huber M-estimation to address gaps in finite-sample validity, causal directionality distinction, and outlier sensitivity.
This paper introduces Topological Causal Data Analysis (TCDA), a framework that integrates stable topological summaries with causal inference to analyze structured outcomes like images and networks, providing identification, estimation, and consistency results for both individual and distribution-level causal effects while clarifying the limits of topology in causal discovery.
The paper introduces DiSAH, a communication-efficient, non-iterative federated algorithm that enables multi-site estimation of hazard differences for survival analysis without sharing patient-level data, achieving accuracy comparable to centralized models while outperforming traditional meta-analysis and local approaches.
This paper proposes a rule-aware Bayesian framework that reconstructs hidden crowd preferences in hybrid expert-crowd systems by modeling latent utilities through dynamic inverse-preference problems, enabling the auditing of aggregation trade-offs and the evaluation of counterfactual decision protocols across 33 seasons of televised competition data.
This study demonstrates that item-adjusted process indicators derived from computer-based assessments significantly improve the prediction of mathematics achievement among Korean students in PISA 2022 beyond traditional questionnaire data, even under a rigorous school-level out-of-sample validation design.
This study developed a practical system of 39 indicators across seven criteria to assess and improve the methodological quality of search strategies in systematic reviews, thereby reducing bias and enhancing reproducibility.
This paper introduces a highly scalable, modular emulator for functional-output simulators that leverages global Gaussian process lengthscale estimates to enable fast local regression, thereby facilitating efficient active learning and rapid calibration of complex multiphysics models while significantly reducing computational costs compared to fully Bayesian approaches.
Using data from a 2018 survey of 4,719 households in flood-affected Kerala, this study demonstrates that evacuation notices significantly increase evacuation likelihood, with targeted in-person warnings proving particularly effective in high-risk and vulnerable populations.