Restricted Hidden Cardinality Constraints in Causal Models
- URL: http://arxiv.org/abs/2109.05656v1
- Date: Mon, 13 Sep 2021 00:52:08 GMT
- Title: Restricted Hidden Cardinality Constraints in Causal Models
- Authors: Beata Zjawin, Elie Wolfe, Robert W. Spekkens
- Abstract summary: Causal models with unobserved variables impose nontrivial constraints on the distributions over the observed variables.
We consider causal models with a promise that unobserved variables have known cardinalities.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Causal models with unobserved variables impose nontrivial constraints on the
distributions over the observed variables. When a common cause of two variables
is unobserved, it is impossible to uncover the causal relation between them
without making additional assumptions about the model. In this work, we
consider causal models with a promise that unobserved variables have known
cardinalities. We derive inequality constraints implied by d-separation in such
models. Moreover, we explore the possibility of leveraging this result to study
causal influence in models that involve quantum systems.
Related papers
- Invariance & Causal Representation Learning: Prospects and Limitations [15.935205681539145]
In causal models, a given mechanism is assumed to be invariant to changes of other mechanisms.
We show that invariance alone is insufficient to identify latent causal variables.
arXiv Detail & Related papers (2023-12-06T16:16:31Z) - Identifiable Latent Polynomial Causal Models Through the Lens of Change [85.67870425656368]
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data.
One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
arXiv Detail & Related papers (2023-10-24T07:46:10Z) - Identifiability Guarantees for Causal Disentanglement from Soft
Interventions [26.435199501882806]
Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model.
In this paper, we focus on the scenario where unpaired observational and interventional data are available, with each intervention changing the mechanism of a latent variable.
When the causal variables are fully observed, statistically consistent algorithms have been developed to identify the causal model under faithfulness assumptions.
arXiv Detail & Related papers (2023-07-12T15:39:39Z) - On the Use of Generative Models in Observational Causal Analysis [0.0]
The use of a hypothetical generative model was been suggested for causal analysis of observational data.
The model describes a single observable distribution and cannot a chain of effects of intervention that deviates from the observed distribution.
arXiv Detail & Related papers (2023-06-07T21:29:49Z) - Nonparametric Identifiability of Causal Representations from Unknown
Interventions [63.1354734978244]
We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables.
Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
arXiv Detail & Related papers (2023-06-01T10:51:58Z) - Weight-variant Latent Causal Models [79.79711624326299]
Causal representation learning exposes latent high-level causal variables behind low-level observations.
In this work we focus on identifying latent causal variables.
We show that the transitivity severely hinders the identifiability of latent causal variables.
We propose a novel method, termed Structural caUsAl Variational autoEncoder, which directly learns latent causal variables.
arXiv Detail & Related papers (2022-08-30T11:12:59Z) - A general framework for cyclic and fine-tuned causal models and their
compatibility with space-time [2.0305676256390934]
Causal modelling is a tool for generating causal explanations of observed correlations.
Existing frameworks for quantum causality tend to focus on acyclic causal structures that are not fine-tuned.
Cyclist causal models can be used to model physical processes involving feedback.
Cyclist causal models may also be relevant in exotic solutions of general relativity.
arXiv Detail & Related papers (2021-09-24T18:00:08Z) - Estimation of Bivariate Structural Causal Models by Variational Gaussian
Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
Causal mechanisms can be described by structural causal models.
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
arXiv Detail & Related papers (2021-09-06T14:52:58Z) - Variational Causal Networks: Approximate Bayesian Inference over Causal
Structures [132.74509389517203]
We introduce a parametric variational family modelled by an autoregressive distribution over the space of discrete DAGs.
In experiments, we demonstrate that the proposed variational posterior is able to provide a good approximation of the true posterior.
arXiv Detail & Related papers (2021-06-14T17:52:49Z) - Discovery of Causal Additive Models in the Presence of Unobserved
Variables [6.670414650224422]
Causal discovery from data affected by unobserved variables is an important but difficult problem to solve.
We propose a method to identify all the causal relationships that are theoretically possible to identify without being biased by unobserved variables.
arXiv Detail & Related papers (2021-06-04T03:28:27Z) - Deconfounded Score Method: Scoring DAGs with Dense Unobserved
Confounding [101.35070661471124]
We show that unobserved confounding leaves a characteristic footprint in the observed data distribution that allows for disentangling spurious and causal effects.
We propose an adjusted score-based causal discovery algorithm that may be implemented with general-purpose solvers and scales to high-dimensional problems.
arXiv Detail & Related papers (2021-03-28T11:07:59Z)
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.