Unsupervised Sparse Multi-Task Learning With Application to Alzheimer's Disease

This article is motivated by the challenge of identifying interpretable brain functional connectivity biomarkers for Alzheimer's disease (AD) progression using high-dimensional functional magnetic resonance imaging (fMRI) data, where predictors comprise both heterogeneous disease-stage activation patterns and strongly similar functional connections. We propose a unified statistical method, called Sparse Multi-task Adaptive Regularization Truncation (SMART), to simultaneously address three critical challenges: (1) High dimensionality is resolved through an ${\ell }_1$ -penalty ( ${\lambda }_1$ ) that selects sparse, stage-distinct functional connections; (2) Disease-stage heterogeneity is accommodated via an ${\ell }_2$ -penalty ( ${\lambda }_2$ ) that maintains stable activation patterns across tasks; (3) Connection collinearity is mitigated using a truncated ${\ell }_2$ penalty (TLP; ${\lambda }_3,\tau$ ) that adaptively groups edges with similar cross-task profiles without pre-specified structure. SMART offers key advantages over existing methods: Its joint regularization naturally handles smooth activation patterns across stages, while the TLP's dual parameters ( $\tau$ for adaptive grouping threshold, ${\lambda }_3$ for sparsity control) provide a principled trade-off between biological fidelity and model complexity. Computationally, we develop a DC-ADMM algorithm that transforms the optimization into tractable subproblems, establishing finite-step convergence to KKT points. Comprehensive simulation studies and real-data analysis of AD neuroimaging data demonstrate SMART's superior accuracy in connectivity biomarker identification, enhanced stability in feature selection, and improved interpretability for AD cohort studies. An accompanying R package, SMART, is available on GitHub ( https://github.com/LDstat/SMART).