A Caltech Library Service

A General Method for Amortizing Variational Filtering

Marino, Joseph and Cvitkovic, Milan and Yue, Yisong (2018) A General Method for Amortizing Variational Filtering. In: Advances in Neural Information Processing Systems 31 (NIPS 2018). Advances in Neural Information Processing Systems. No.31. Curran Associates , Red Hook, NY, pp. 1-12.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.


Use this Persistent URL to link to this item:


We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and consists of an optimization procedure at each time step. By performing each inference optimization procedure with an iterative amortized inference model, we obtain a computationally efficient implementation of the algorithm, which we call amortized variational filtering. We present experiments demonstrating that this general-purpose method improves performance across several deep dynamical latent variable models.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Marino, Joseph0000-0001-6387-8062
Yue, Yisong0000-0001-9127-1989
Additional Information:© 2018 Neural Information Processing Systems Foundation, Inc. We would like to thank Matteo Ruggero Ronchi for helpful discussions. This work was supported by the following grants: JPL PDF 1584398, NSF 1564330, and NSF 1637598.
Funding AgencyGrant Number
JPL President and Director's Fund1584398
Series Name:Advances in Neural Information Processing Systems
Issue or Number:31
Record Number:CaltechAUTHORS:20190205-101451102
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92660
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 19:05
Last Modified:11 Nov 2020 00:27

Repository Staff Only: item control page