paper-with-me

Papers

Graphical Normalizing Flows

2020-06-03 · Antoine Wehenkel, Gilles Louppe

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.

📄 PDF Abstract BibTeX arXiv:2006.02548

Code (4)

AWehenkel/DAG-NF 공식 구현 pytorch
AWehenkel/Graphical-Normalizing-Flows pytorch
metachenyiyan/BreezeForest pytorch
sobalgi/rhognf pytorch

Tasks

Density Estimation

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Graphical Residual Flows

2022-04-23 · Jacobie Mouton, Steve Kroon

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 Estimation

You say Normalizing Flows I see Bayesian Networks

2020-06-01 · Antoine Wehenkel, Gilles Louppe

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

2019-10-16 · pproximateinference AABI Symposium 2019 12 · Christian Weilbach, Boyan Beronov, William Harvey, Frank Wood

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 Programming

Self-Supervised Learning of Generative Spin-Glasses with Normalizing Flows

2020-01-02 · Gavin S. Hartnett, Masoud Mohseni

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 Learning

Counterfactual Analysis of the Impact of the IMF Program on Child Poverty in the Global-South Region using Causal-Graphical Normalizing Flows

2022-02-17 · Sourabh Balgi, Jose M. Peña, Adel Daoud

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