Neural Distribution Learning for generalized time-to-event prediction

Egil Martinsson, Adrian Kim, Jaesung Huh, Jaegul Choo, Jung-Woo Ha

Sep 27, 2018 ICLR 2019 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Predicting the time to the next event is an important task in various domains. However, due to censoring and irregularly sampled sequences, time-to-event prediction has resulted in limited success only for particular tasks, architectures and data. Using recent advances in probabilistic programming and density networks, we make the case for a generalized parametric survival approach, sequentially predicting a distribution over the time to the next event. Unlike previous work, the proposed method can use asynchronously sampled features for censored, discrete, and multivariate data. Furthermore, it achieves good performance and near perfect calibration for probabilistic predictions without using rigid network-architectures, multitask approaches, complex learning schemes or non-trivial adaptations of cox-models. We firmly establish that this can be achieved in the standard neural network framework by simply switching out the output layer and loss function.
  • Keywords: Deep Learning, Survival Analysis, Event prediction, Time Series, Probabilistic Programming, Density Networks
  • TL;DR: We present a general solution to event prediction that has been there all along; Discrete Time Parametric Survival Analysis.
0 Replies