Timezone: »
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.
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)
-
2019 Oral: Discriminative Regularization for Latent Variable Models with Applications to Electrocardiography »
Wed. Jun 12th 11:25 -- 11:30 PM Room Hall B
More from the Same Authors
-
2023 : Practical and Asymptotically Exact Conditional Sampling in Diffusion Models »
Brian Trippe · Luhuan Wu · Christian Naesseth · David Blei · John Cunningham -
2022 Poster: Scaling Structured Inference with Randomization »
Yao Fu · John Cunningham · Mirella Lapata -
2022 Spotlight: Scaling Structured Inference with Randomization »
Yao Fu · John Cunningham · Mirella Lapata -
2022 Poster: Preconditioning for Scalable Gaussian Process Hyperparameter Optimization »
Jonathan Wenger · Geoff Pleiss · Philipp Hennig · John Cunningham · Jacob Gardner -
2022 Oral: Preconditioning for Scalable Gaussian Process Hyperparameter Optimization »
Jonathan Wenger · Geoff Pleiss · Philipp Hennig · John Cunningham · Jacob Gardner -
2020 : Panel Discussion »
Subhashini Venugopalan · Eun-Ah Kim · Barbara Engelhardt · Sendhil Mullainathan · Arunachalam Narayanaswamy · Katherine Bouman -
2020 : Q&A - Sendhil Mullainathan »
Sendhil Mullainathan · Subhashini Venugopalan -
2020 : Invited Talk - Sendhil Mullainathan, Machine Learning for Scientific Discovery (recorded) »
Sendhil Mullainathan · Subhashini Venugopalan -
2020 Poster: The continuous categorical: a novel simplex-valued exponential family »
Elliott Gordon-Rodriguez · Gabriel Loaiza-Ganem · John Cunningham -
2018 Poster: Semi-Amortized Variational Autoencoders »
Yoon Kim · Sam Wiseman · Andrew Miller · David Sontag · Alexander Rush -
2018 Oral: Semi-Amortized Variational Autoencoders »
Yoon Kim · Sam Wiseman · Andrew Miller · David Sontag · Alexander Rush -
2017 Poster: Variational Boosting: Iteratively Refining Posterior Approximations »
Andrew Miller · Nicholas J Foti · Ryan P. Adams -
2017 Talk: Variational Boosting: Iteratively Refining Posterior Approximations »
Andrew Miller · Nicholas J Foti · Ryan P. Adams