• Corpus ID: 52939588

Learning discrete Bayesian networks in polynomial time and sample complexity

@inproceedings{Barik2018LearningDB,
  title={Learning discrete Bayesian networks in polynomial time and sample complexity},
  author={Adarsh Barik and Jean Honorio},
  year={2018}
}
In this paper, we study the problem of structure learning for Bayesian networks in which nodes take discrete values. The problem is NP-hard in general but we show that under certain conditions we can recover the true structure of a Bayesian network with sufficient number of samples. We develop a mathematical model which does not assume any specific conditional probability distributions for the nodes. We use a primal-dual witness construction to prove that, under some technical conditions on the… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 37 REFERENCES
Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
TLDR
A provably polynomial-time algorithm for learning sparse Gaussian Bayesian networks with equal noise variance --- a class ofBayesian networks for which the DAG structure can be uniquely identified from observational data --- under high-dimensional settings is proposed.
Parameterized Complexity Results for Exact Bayesian Network Structure Learning
TLDR
This paper studies the computational worst-case complexity of exact Bayesian network structure learning under graph theoretic restrictions on the (directed) super-structure and introduces the directed super-Structure as a natural generalization of its undirected counterpart.
Large-Sample Learning of Bayesian Networks is NP-Hard
TLDR
It is shown that identifying high-scoring structures is NP-hard, even when the authors are given an independence oracles, an inference oracle, and/or an information oracle.
Exact Bayesian Structure Discovery in Bayesian Networks
TLDR
This work presents an algorithm that computes the exact posterior probability of a subnetwork, e.g., a directed edge, and shows that also in domains with a large number of variables, exact computation is feasible, given suitable a priori restrictions on the structures.
Bayesian Network Induction via Local Neighborhoods
TLDR
This work presents an efficient algorithm for learning Bayes networks from data by first identifying each node's Markov blankets, then connecting nodes in a maximally consistent way, and proves that under mild assumptions, the approach requires time polynomial in the size of the data and the number of nodes.
Learning Bayesian Network Structure using LP Relaxations
TLDR
This work proposes to solve the combinatorial problem ofding the highest scoring Bayesian network structure from data by maintaining an outer bound approximation to the polytope and iteratively tighten it by searching over a new class of valid constraints.
A Simple Approach for Finding the Globally Optimal Bayesian Network Structure
TLDR
It is shown that it is possible to learn the best Bayesian network structure with over 30 variables, which covers many practically interesting cases and offers a possibility for efficient exploration of the best networks consistent with different variable orderings.
SparsityBoost: A New Scoring Function for Learning Bayesian Network Structure
TLDR
A polynomial sample complexity result is proved, showing that maximizing this score is guaranteed to correctly learn a structure with no false edges and a distribution close to the generating distribution, whenever there exists a Bayesian network which is a perfect map for the data generating distribution.
Learning Bayesian Network Structure from Massive Datasets: The "Sparse Candidate" Algorithm
TLDR
An algorithm that achieves faster learning by restricting the search space, which restricts the parents of each variable to belong to a small subset of candidates and is evaluated both on synthetic and real-life data.
Impact of Learning Strategies on the Quality of Bayesian Networks: An Empirical Evaluation
TLDR
It is found that learning strategies with weak optimality guarantees show good performance on synthetic datasets, but, compared to exact approaches, perform poorly on the more "real-world" datasets.
...
1
2
3
4
...