Towards Recurrent Autoregressive Flow Models
Abstract
Stochastic processes generated by non-stationary distributions are difficult to represent with conventional models such as Gaussian processes. This work presents Recurrent Autoregressive Flows as a method toward general stochastic process modeling with normalizing flows. The proposed method defines a conditional distribution for each variable in a sequential process by conditioning the parameters of a normalizing flow with recurrent neural connections. Complex conditional relationships are learned through the recurrent network parameters. In this work, we present an initial design for a recurrent flow cell and a method to train the model to match observed empirical distributions. We demonstrate the effectiveness of this class of models through a series of experiments in which models are trained on three complex stochastic processes. We highlight the shortcomings of our current formulation and suggest some potential solutions.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 17, 2020
- Accession Number
- AD1148754
Entities
People
- John Mern
- Mykel Kochenderfer
- Peter Morales
Organizations
- MIT Lincoln Laboratory
- Stanford University