Timezone: »

 
Poster
Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography
Andrew Miller · Ziad Obermeyer · John Cunningham · Sendhil Mullainathan

Wed Jun 12 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #53
in Posters Wed »

Generative models often use latent variables to represent structured variation in high-dimensional data, such as images and medical waveforms. However, these latent variables may ignore subtle, yet meaningful features in the data. Some features may predict an outcome of interest (e.g. heart attack) but account for only a small fraction of variation in the data. We propose a generative model training objective that uses a black-box discriminative model as a regularizer to learn representations that preserve this predictive variation. With these discriminatively regularized latent variable models, we visualize and measure variation in the data that influence a black-box predictive model, enabling an expert to better understand each prediction. With this technique, we study models that use electrocardiograms to predict outcomes of clinical interest. We measure our approach on synthetic and real data with statistical summaries and an experiment carried out by a physician.

Keywords: Approximate Inference · Deep Generative Models · Generative Models · Healthcare · Representation Learning

Author Information

Andrew Miller (Columbia University)
Ziad Obermeyer (UC Berkeley)
John Cunningham (Columbia)
Sendhil Mullainathan (University of Chicago)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors