arXiv subjects

Mayu Hiraishi

Publications and source records attributed to Mayu Hiraishi.

5 recordsLinked to original sources

arXiv2026

Geographically Regularized AUC-Maximizing Personalized Federated Learning

Accurate diagnostic and risk-prediction models are important for supporting clinical decision-making during infectious disease outbreaks. However, privacy and governance requirements may restrict patient-level data sharing across healthcare institutions, and data distributions often vary. Moreover, AUC is widely used to evaluate discriminative performance, motivating its direct optimization in model development. We propose geographically regularized AUC-maximizing personalized federated learning (GrAUC-PFL), which directly optimizes a smooth pairwise AUC surrogate to learn personalized models while keeping patient-level data local and accounting for institutional heterogeneity. Graph-based regularization encourages geographically neighboring institutions to have similar coefficient vectors while retaining a personalized models. Simulations and a real-data application suggest improved discriminative performance, particularly when geographically neighboring institutions have similar data-generating characteristics.

cs.LG↗

arXiv2025

Regularized Sparse Optimal Discriminant Clustering

We propose a new method based on sparse optimal discriminant clustering (SODC), incorporating a penalty term into the scoring matrix based on convex clustering. With the addition of this penalty term, it is expected to improve the accuracy of cluster identification by pulling points within the same cluster closer together and points from different clusters further apart. When the estimation results are visualized, the clustering structure can be depicted more clearly. Moreover, we develop a novel algorithm to derive the updated formula of this scoring matrix using a majorizing function. The scoring matrix is updated using the alternating direction method of multipliers (ADMM), which is often employed to calculate the parameters of the objective function in the convex clustering. In the proposed method, as in the conventional SODC, the scoring matrix is subject to an orthogonal constraint. Therefore, it is necessary to satisfy the orthogonal constraint on the scoring matrix while maintaining the clustering structure. Using a majorizing function, we adress the challenge of enforcing both orthogonal constraint and the clustering structure within the scoring matrix. We demonstrate numerical simulations and an application to real data to assess the performance of the proposed method.

stat.ME↗

arXiv2025

Wilcoxon-type Multivariate Cluster Elastic Net

We propose a method for high dimensional multivariate regression that is robust to random error distributions that are heavy-tailed or contain outliers, while preserving estimation accuracy in normal random error distributions. We extend the Wilcoxon-type regression to a multivariate regression model as a tuning-free approach to robustness. Furthermore, the proposed method regularizes the L1 and L2 terms of the clustering based on k-means, which is extended from the multivariate cluster elastic net. The estimation of the regression coefficient and variable selection are produced simultaneously. Moreover, considering the relationship among the correlation of response variables through the clustering is expected to improve the estimation performance. Numerical simulation demonstrates that our proposed method overperformed the multivariate cluster method and other methods of multiple regression in the case of heavy-tailed error distribution and outliers. It also showed stability in normal error distribution. Finally, we confirm the efficacy of our proposed method using a data example for the gene associated with breast cancer.

stat.ME↗

arXiv2023

Causal rule ensemble method for estimating heterogeneous treatment effect with consideration of main effects

This study proposes a novel framework based on the RuleFit method to estimate Heterogeneous Treatment Effect (HTE) in a randomized clinical trial. To achieve this, we adopted S-learner of the metaalgorithm for our proposed framework. The proposed method incorporates a rule term for the main effect and treatment effect, which allows HTE to be interpretable form of rule. By including a main effect term in the proposed model, the selected rule is represented as an HTE that excludes other effects. We confirmed a performance equivalent to that of another ensemble learning methods through numerical simulation and demonstrated the interpretation of the proposed method from a real data application.

stat.ME↗

arXiv2021

Concordance Rate of a Four-Quadrant Plot for Repeated Measurements

Before new clinical measurement methods are implemented in clinical practice, it must be confirmed whether their results are equivalent to those of existing methods. The agreement of the trend between these methods is evaluated using the four-quadrant plot, which describes the trend of change in each difference of the two measurement methods' values in sequential time points, and the plot's concordance rate, which is calculated using the sum of data points in the four-quadrant plot that agree with this trend divided by the number of all accepted data points. However, the conventional concordance rate does not consider the covariance between the data on individual subjects, which may affect its proper evaluation. Therefore, we proposed a new concordance rate calculated by each individual according to the number of agreement. Moreover, this proposed method can set a parameter that the minimum concordant number between two measurement techniques. The parameter can provide a more detailed interpretation of the degree of agreement. A numerical simulation conducted with several factors indicated that the proposed method resulted in a more accurate evaluation. We also showed a real data and compared the proposed method with the conventional approach. Then, we concluded the discussion with the implementation in clinical studies.

stat.ME↗