Deep Kalman Filters

Kalman Filters are one of the most influential models of time-varying phenomena. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption in a variety of disciplines. Motivated by recent variational methods for learning deep generative models, we introduce a unified algorithm to efficiently learn a broad spectrum of Kalman filters. Of particular interest is the use of temporal generative models for counterfactual inference. We investigate the efficacy of such models for counterfactual inference, and to that end we introduce the "Healing MNIST" dataset where long-term structure, noise and actions are applied to sequences of digits. We show the efficacy of our method for modeling this dataset. We further show how our model can be used for counterfactual inference for patients, based on electronic health record data of 8,000 patients over 4.5 years.

[1]  Illtyd Trethowan.  Causality , 1938 .

[2]  T. Shakespeare,et al.  Observational Studies , 2003 .

[3]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[4]  S. Haykin.  Kalman Filtering and Neural Networks , 2001 .

[5]  Michael J. Grimble,et al.  Adaptive systems for signal processing, communications and control , 2001 .

[6]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[7]  Juha Karhunen,et al.  An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models , 2002, Neural Computation.

[8]  M. Höfler,et al.  Causal inference based on counterfactuals , 2005, BMC medical research methodology.

[9]  Yann LeCun,et al.  Dynamic Factor Graphs for Time Series Modeling , 2009, ECML/PKDD.

[10]  Tapani Raiko,et al.  Variational Bayesian learning of nonlinear hidden state-space models for model predictive control , 2009, Neurocomputing.

[11]  John Langford,et al.  Learning nonlinear dynamic models , 2009, ICML '09.

[12]  E. Tabak,et al.  DENSITY ESTIMATION BY DUAL ASCENT OF THE LOG-LIKELIHOOD ∗ , 2010 .

[13]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[14]  Joaquin Quiñonero Candela,et al.  Counterfactual reasoning and learning systems: the example of computational advertising , 2013, J. Mach. Learn. Res..

[15]  Roland Memisevic,et al.  Learning to Relate Images , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Wojciech Zaremba,et al.  Learning to Execute , 2014, ArXiv.

[17]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[18]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[19]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[20]  Christian Osendorfer,et al.  Learning Stochastic Recurrent Networks , 2014, NIPS 2014.

[21]  Zhe Gan,et al.  Deep Temporal Sigmoid Belief Networks for Sequence Modeling , 2015, NIPS.

[22]  Yoshua Bengio,et al.  A Recurrent Latent Variable Model for Sequential Data , 2015, NIPS.

[23]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[24]  Nitish Srivastava,et al.  Unsupervised Learning of Video Representations using LSTMs , 2015, ICML.

[25]  Alex Graves,et al.  DRAW: A Recurrent Neural Network For Image Generation , 2015, ICML.

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Martin A. Riedmiller,et al.  Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images , 2015, NIPS.

[28]  Yann LeCun,et al.  Learning to Linearize Under Uncertainty , 2015, NIPS.

[29]  Florian Nadel,et al.  Stochastic Processes And Filtering Theory , 2016 .