Tag
HB-PVI is a hierarchical Bayesian framework that optimizes personalization decisions in complex activity recognition by balancing gains and costs, demonstrating that a population-first deployment policy can reduce labeling expenses while maintaining performance.
Proposes a hierarchical Bayesian framework for meta-learning in dynamical systems from multiple sparse, noisy datasets, using gradient-based MCMC with an embedded ODE solver for efficient posterior inference of shared and dataset-specific parameters.