Jackknife bias‐corrected variance estimation for the generalized regression estimator
Canadian Journal of Statistics, EarlyView.Abstract Commonly used variance estimators for the generalized regression estimator (GREG) are based on Taylor linearization and jackknife. Traditionally, a jackknife GREG variance estimator is obtained by jackknifing GREG, which consists of computing GREG from each of several subsamples of the parent sample, and estimating the variance of the parent ...
Marius Stefan, J.N.K Rao
wiley +1 more source
Dynamic survival risk prediction with time‐varying high‐dimensional images
Canadian Journal of Statistics, EarlyView.Abstract Integrating longitudinal data with survival models is a prevalent strategy for dynamic survival risk prediction while accounting for subjects' longitudinally observed variables. However, existing methods primarily focus on scalar longitudinal data and seldom tackle the complexities associated with high‐dimensional longitudinal imaging data ...
Bingfan Liu +7 more
wiley +1 more source
Copula‐based joint modelling of emergency department visits with time‐varying dependence
Canadian Journal of Statistics, EarlyView.Abstract Jointly modelling multiple correlated count time series is essential in health services research, where outcomes like emergency visits for mental health and substance use often evolve together. Ignoring these dependencies can obscure meaningful trends and limit the effectiveness of policy evaluation.
Guanjie Lyu, Cindy Feng, Lihui Liu
wiley +1 more source
Global Convergence of Continual Learning on Non-IID Data
CoRRContinual learning, which aims to learn multiple tasks sequentially, has gained extensive attention. However, most existing work focuses on empirical studies, and the theoretical aspect remains under-explored. Recently, a few investigations have considered the theory of continual learning only for linear regressions, establishes the results based on ...
Fei Zhu 0004 +3 more
openaire +3 more sources
DAG-Based Blockchain Sharding for Secure Federated Learning with Non-IID Data. [PDF]
Sensors (Basel), 2022 Lee J, Kim W.
europepmc +1 more source
Improving Non-IID federated survival analysis with data augmentation and gradient boosted trees
Data-driven machine learning models have increasingly been applied to survival analysis in recent years. However, these models require sufficient training samples, which is often impractical due to privacy, security, and legal constraints.
Wang, H +4 more
core +1 more source
Feature Matching Data Synthesis for Non-IID Federated Learning
, 2023 Federated learning (FL) has emerged as a privacy-preserving paradigm that trains neural networks on edge devices without collecting data at a central server.
Sun, Yuchang +5 more
core
Vine copula knockoffs for variable selection in gene expression studies
Canadian Journal of Statistics, EarlyView.Abstract Identifying clinical and genetic markers is essential for stratifying cancer patients by survival outcomes and guiding personalized treatment strategies. However, gene expression studies often involve high‐dimensional predictors with mixed data types and complex dependence, which complicates reliable variable selection.
José Ulises Márquez Urbina +3 more
wiley +1 more source
CHPFL: Clustered adaptive hierarchical federated learning for edge-level personalization
High-Confidence ComputingFederated learning faces challenges with non-IID data distributions, often resulting in suboptimal performance for individual clients with the global model. To address this issue, we propose a clustered hierarchical personalized federated learning (CHPFL)
Lihua Song +4 more
doaj +1 more source
Adversarially-Regularized Mixed Effects Deep Learning (ARMED) Models Improve Interpretability, Performance, and Generalization on Clustered (non-iid) Data. [PDF]
IEEE Trans Pattern Anal Mach Intell, 2023 Nguyen KP, Treacher AH, Montillo AA.
europepmc +1 more source