Bayesian Anchored Latent Learning for Estimating State Trajectories
Gibbons, J. B.; Leenaerts, N.; Mandavia, A. D.; Jameson, J. C.; Liang, A.; Hathaway, D.; Yang, J.; Gu, B.; Marx, B. P.; Siddiqi, S.; Wood, R.; Ruble, M.; Lyndon, S.; Wang, P. S.
Show abstract
Dynamic systems often evolve faster than reliable measurements can be collected. More frequent indirect observations may fill these gaps, but their noise and differing scales complicate estimation of the underlying state. We developed Bayesian Anchored Latent Learning (BALL) to combine sparse reference measurements with denser records on an interpretable scale. A bidirectional transformer teacher reconstructs trajectories from complete training histories, and a forward-only transformer student learns from those reconstructions and observed measurements. Across 30 simulations, BALL reduced composite trajectory error by 7% relative to the same transformer trained directly from measurements, achieving lower error across all datasets. In an applied example using psychiatric records from 1,609 patients, BALL improved the prediction of withheld questionnaire scores compared with direct transformer training at 21- and 28-day measurement schedules. Requests guided by estimated uncertainty further improved prediction. BALL connects retrospective learning with prospective state estimation and provides a framework for directing additional measurement.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Generation of realistic synthetic data using multimodal neural ordinary differential equations 94%
- Identifying Importation and Asymptomatic Spreaders of Multi-drug Resistant Organisms in Hospital Settings 92%
- Computational network models for forecasting and control of mental health trajectories in digital applications 92%
Similar papers in this journal
Similar papers in this journal
- Safe Blues: A Method for Estimation and Control in the Fight Against COVID-19 91%
- Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer 91%
- Generating hard-to-obtain information from easy-to-obtain information: applications in drug discovery and clinical inference 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.