Nonparametric Bayesian networks are typically faithful in the total variation metric

• URL: http://arxiv.org/abs/2410.16004v1
• Date: Mon, 21 Oct 2024 13:38:04 GMT
• Title: Nonparametric Bayesian networks are typically faithful in the total variation metric
• Authors: Philip Boeken, Patrick Forré, Joris M. Mooij,
• Abstract summary: We show that for a given DAG $G$, among all observational distributions of Bayesian networks over $G$ with arbitrary outcome spaces, the faithful distributions are typical' As a consequence, the set of faithful distributions is non-empty, and the unfaithful distributions are nowhere dense.
• Score: 12.27570686178551
• License:
• Abstract: We show that for a given DAG $G$, among all observational distributions of Bayesian networks over $G$ with arbitrary outcome spaces, the faithful distributions are `typical': they constitute a dense, open set with respect to the total variation metric. As a consequence, the set of faithful distributions is non-empty, and the unfaithful distributions are nowhere dense. We extend this result to the space of Bayesian networks, where the properties hold for Bayesian networks instead of distributions of Bayesian networks. As special cases, we show that these results also hold for the faithful parameters of the subclasses of linear Gaussian -- and discrete Bayesian networks, giving a topological analogue of the measure-zero results of Spirtes et al. (1993) and Meek (1995). Finally, we extend our topological results and the measure-zero results of Spirtes et al. and Meek to Bayesian networks with latent variables.

Related papers

• Feature learning in finite-width Bayesian deep linear networks with multiple outputs and convolutional layers [39.71511919246829]
  Deep linear networks have been extensively studied, but little is known in the case of finite-width architectures with multiple outputs and convolutional layers. Our work provides a dictionary that translates this physics intuition and terminology into rigorous Bayesian statistics.
  arXiv  Detail & Related papers  (2024-06-05T13:37:42Z)
• A Note on Bayesian Networks with Latent Root Variables [56.86503578982023]
  We show that the marginal distribution over the remaining, manifest, variables also factorises as a Bayesian network, which we call empirical. A dataset of observations of the manifest variables allows us to quantify the parameters of the empirical Bayesian net.
  arXiv  Detail & Related papers  (2024-02-26T23:53:34Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Wrapped Distributions on homogeneous Riemannian manifolds [58.720142291102135]
  Control over distributions' properties, such as parameters, symmetry and modality yield a family of flexible distributions. We empirically validate our approach by utilizing our proposed distributions within a variational autoencoder and a latent space network model.
  arXiv  Detail & Related papers  (2022-04-20T21:25:21Z)
• Robust Estimation for Nonparametric Families via Generative Adversarial Networks [92.64483100338724]
  We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems. Our work extend these to robust mean estimation, second moment estimation, and robust linear regression. In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
  arXiv  Detail & Related papers  (2022-02-02T20:11:33Z)
• Semiparametric Bayesian Networks [5.205440005969871]
  We introduce semiparametric Bayesian networks that combine parametric and nonparametric conditional probability distributions. Their aim is to incorporate the bounded complexity of parametric models and the flexibility of nonparametric ones.
  arXiv  Detail & Related papers  (2021-09-07T11:47:32Z)
• Reconsidering Dependency Networks from an Information Geometry Perspective [2.6778110563115542]
  Dependency networks are potential probabilistic graphical models for systems comprising a large number of variables. The structure of a dependency network is represented by a directed graph, and each node has a conditional probability table. We show that the dependency network and the Bayesian network have roughly the same performance in terms of the accuracy of their learned distributions.
  arXiv  Detail & Related papers  (2021-07-02T07:05:11Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.