Graphical Residual Flows
This work addresses a bottleneck in machine learning for probabilistic modeling by enabling bidirectional tasks with a single model, though it is incremental as it builds on existing graphical flow and invertible network concepts.
The paper tackled the problem of creating graphical flow models that can perform both density estimation and inference tasks efficiently by introducing graphical residual flows based on invertible residual networks, achieving stable and accurate inversion that is more time-efficient than alternative flows while maintaining competitive performance.
Graphical flows add further structure to normalizing flows by encoding non-trivial variable dependencies. Previous graphical flow models have focused primarily on a single flow direction: the normalizing direction for density estimation, or the generative direction for inference. However, to use a single flow to perform tasks in both directions, the model must exhibit stable and efficient flow inversion. This work introduces graphical residual flows, a graphical flow based on invertible residual networks. Our approach to incorporating dependency information in the flow, means that we are able to calculate the Jacobian determinant of these flows exactly. Our experiments confirm that graphical residual flows provide stable and accurate inversion that is also more time-efficient than alternative flows with similar task performance. Furthermore, our model provides performance competitive with other graphical flows for both density estimation and inference tasks.