252 papers
This paper presents a systematic framework for optimizing position-independent irreversible perturbations in the Unadjusted Langevin Algorithm by formulating a constrained optimization problem that balances mixing efficiency and discretization bias, resulting in an explicit optimal design that achieves faster convergence with controlled error.
This study employs an objective Entropy-Weight WRSR model to analyze the 2024 Olympic Women's Basketball Final, identifying three-point shooting, foul control, steals, and blocks as key determinants and revealing that the French team's significant performance deviations in steals and blocks under pressure highlight systemic weaknesses in their defense and decision-making compared to the dominant USA team.
This paper introduces a new heteroskedastic structural model that estimates area-specific variability and lagged spatial impacts without assuming cross-sectional homoscedasticity, demonstrated through an analysis of the relationship between global temperature, fossil fuel use, and carbon emissions across seven South American countries.
This paper proposes an efficient reliability analysis method that integrates local Gaussian processes, a novel adaptive learning function, and active subspaces to overcome the limitations of global optimization-based approaches in estimating failure probabilities for highly nonlinear, high-dimensional rare-event problems.
This paper introduces EPR-C3, a deterministic, constraint-aware heuristic that efficiently identifies high-quality, statistically admissible predictor subsets for high-dimensional multiple linear regression by combining structured neighborhood search with specific refinement steps, offering a computationally tractable alternative to exhaustive enumeration while outperforming existing selection methods.
This study utilizes Monte Carlo simulations and empirical validation to identify optimal combinations of missing data imputation and confounder control strategies for longitudinal causal inference, demonstrating that multiple imputation or random forest paired with doubly robust estimation yields the best performance for heterogeneous effects without unmeasured confounding.
This paper proposes a generalized six-equation SEIR model incorporating re-infections, newborns, vaccinations, and an exposed compartment to address previous limitations, introduces a new reproduction number based on exposed population dynamics for epidemic control, and utilizes this framework to predict a resurgence of pertussis cases in England during mid-to-late 2027.
This study demonstrates that recalculating journal impact factors by excluding extreme citation outliers from the document sample, with an optimal retention threshold of 90%, effectively reduces indicator fluctuations and enhances the stability and rationality of journal evaluation systems.
This paper demonstrates that a network's variance-weighted social power (F) simultaneously dictates the minimum information cost required to steer a group's consensus to a false value and the difficulty of detecting such an attack, revealing that concentrating influence to improve collective accuracy inherently increases the network's vulnerability to undetectable manipulation.
This paper introduces Sketch-FORCE, a sub-quadratic streaming algorithm that combines robust scale tracking with Frequent Directions matrix sketching to enable efficient, memory-light covariance estimation for high-dimensional data under heavy-tailed contamination and adversarial outliers.