34: Modeling Heterogeneity with Generative Latent Contexts for Effective Transfer Learning

Thomas M. Menino Convention & Exhibition Center 

Learning predictive models in heterogeneous, resource-limited settings is challenging: local models lack statistical power, while standard transfer learning methods often fail to adapt to context-specific structure. We introduce Contextualized Transfer Learning (CTL), a framework that models context-dependent prediction through shared latent representations, enabling information sharing across related tasks while preserving individualized adaptation. We derive learning bounds for CTL under stability and learnability conditions, characterizing its generalization behavior. Empirically, CTL achieves predictive performance comparable to state-of-the-art black-box models while providing individual-level interpretability through its structured parameterization, making it a principled and interpretable approach for learning under heterogeneity.

Learning Theory

Transfer Learning

Contextualized Learning 

Section on Statistical Learning and Data Science