Graphical Normalizing Flows
Normalizing flows model complex probability distributions by combining a base distribution with a series of bijective neural networks. State-of-the-art architectures rely on coupling and autoregressive transformations to lift up invertible functions from scalars to vectors. In this work, we revisit these transformations as probabilistic graphical models, showing they reduce to Bayesian networks with a pre-defined topology and a learnable density at each node. From this new perspective, we propose the graphical normalizing flow, a new invertible transformation with either a prescribed or a learnable graphical structure. This model provides a promising way to inject domain knowledge into normalizing flows while preserving both the interpretability of Bayesian networks and the representation capacity of normalizing flows. We show that graphical conditioners discover relevant graph structure when we cannot hypothesize it. In addition, we analyze the effect of $\ell_1$-penalization on the recovered structure and on the quality of the resulting density estimation. Finally, we show that graphical conditioners lead to competitive white box density estimators. Our implementation is available at https://github.com/AWehenkel/DAG-NF.
Code (4)
Tasks
Density EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Graphical Residual Flows
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 de…
Density EstimationYou say Normalizing Flows I see Bayesian Networks
Normalizing flows have emerged as an important family of deep neural networks for modelling complex probability distributions. In this note, we revisit their coupling and autoregressive transformation layers as probabili…
Efficient Inference Amortization in Graphical Models using Structured Continuous Conditional Normalizing Flows
We introduce a more efficient neural architecture for amortized inference, which combines continuous and conditional normalizing flows using a principled choice of structure. Our gradient flow derives its sparsity patter…
Probabilistic ProgrammingSelf-Supervised Learning of Generative Spin-Glasses with Normalizing Flows
Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimization, inference in graphical models, and au…
Self-Supervised LearningCounterfactual Analysis of the Impact of the IMF Program on Child Poverty in the Global-South Region using Causal-Graphical Normalizing Flows
This work demonstrates the application of a particular branch of causal inference and deep learning models: \emph{causal-Graphical Normalizing Flows (c-GNFs)}. In a recent contribution, scholars showed that normalizing f…
Causal InferencecounterfactualCounterfactual Inference