Variational inference is an umbrella term for algorithms which cast Bayesian inference as
optimization. Classically, variational inference uses the Kullback-Leibler divergence to define …

Variational inference has become a widely used method to approximate posteriors in complex
latent variables models. However, deriving a variational inference algorithm generally …

Electrocardiogram (ECG) acquisition is increasingly widespread in medical and commercial
devices, necessitating the development of automated interpretation strategies. Recently, …

Clinical notes contain information about patients that goes beyond structured data like lab
values and medications. However, clinical notes have been underused relative to structured …

Machine learning for health must be reproducible to ensure reliable clinical use. We evaluated
511 scientific papers across several machine learning subfields and found that machine …

There has been much interest in unsupervised learning of hierarchical generative models
such as deep belief networks. Scaling such models to full-sized, high-dimensional images …

Probabilistic modeling is iterative. A scientist posits a simple model, fits it to her data, refines
it according to her analysis, and repeats. However, fitting complex models to large data is a …

Black box variational inference allows researchers to easily prototype and evaluate an array
of models. Recent advances allow such algorithms to scale to high dimensions. However, a …

Modern electronic health records (EHRs) provide data to answer clinically meaningful
questions. The growing data in EHRs makes healthcare ripe for the use of machine learning. …

There has been much interest in unsupervised learning of hierarchical generative models
such as deep belief networks (DBNs); however, scaling such models to full-sized, high-…