Dags with no tears: Continuous optimization for structure learning

X Zheng, B Aragam, PK Ravikumar… - Advances in neural …, 2018 - proceedings.neurips.cc
Estimating the structure of directed acyclic graphs (DAGs, also known as Bayesian
networks) is a challenging problem since the search space of DAGs is combinatorial and …

DAG-GNN: DAG structure learning with graph neural networks

Y Yu, J Chen, T Gao, M Yu - International conference on …, 2019 - proceedings.mlr.press
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a
challenging combinatorial problem, owing to the intractable search space superexponential …

DAGs with no curl: An efficient DAG structure learning approach

Y Yu, T Gao, N Yin, Q Ji - International Conference on …, 2021 - proceedings.mlr.press
Recently directed acyclic graph (DAG) structure learning is formulated as a constrained
continuous optimization problem with continuous acyclicity constraints and was solved …

Learning large-scale Bayesian networks with the sparsebn package

B Aragam, J Gu, Q Zhou - Journal of Statistical Software, 2019 - jstatsoft.org
Learning graphical models from data is an important problem with wide applications,
ranging from genomics to the social sciences. Nowadays datasets often have upwards of …

Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential families

G Rajendran, B Kivva, M Gao… - Advances in Neural …, 2021 - proceedings.neurips.cc
Greedy algorithms have long been a workhorse for learning graphical models, and more
broadly for learning statistical models with sparse structure. In the context of learning …

Bayesian network structure learning with integer programming: Polytopes, facets and complexity

J Cussens, M Järvisalo, JH Korhonen… - Journal of Artificial …, 2017 - jair.org
The challenging task of learning structures of probabilistic graphical models is an important
problem within modern AI research. Recent years have witnessed several major algorithmic …

Simultaneous missing value imputation and structure learning with groups

P Morales-Alvarez, W Gong, A Lamb… - Advances in …, 2022 - proceedings.neurips.cc
Learning structures between groups of variables from data with missing values is an
important task in the real world, yet difficult to solve. One typical scenario is discovering the …

Integer programming for learning directed acyclic graphs from continuous data

H Manzour, S Küçükyavuz, HH Wu… - INFORMS Journal on …, 2021 - pubsonline.informs.org
Learning directed acyclic graphs (DAGs) from data is a challenging task both in theory and
in practice, because the number of possible DAGs scales superexponentially with the …

Student model construction of intelligent teaching system based on Bayesian network

L Wu - Personal and Ubiquitous Computing, 2020 - Springer
The intelligent teaching system is the most important in the field of teaching. It uses artificial
intelligence technology to bring a lot of help to learners in terms of knowledge and skill …

Optimal transport for structure learning under missing data

V Vo, H Zhao, T Le, EV Bonilla, D Phung - arxiv preprint arxiv:2402.15255, 2024 - arxiv.org
Causal discovery in the presence of missing data introduces a chicken-and-egg dilemma.
While the goal is to recover the true causal structure, robust imputation requires considering …