Sort by
Most Relevant
Most Popular
Least Popular
Most Recent
Least Recent

Total Results 128

*
*
We consider the problem of inferring causal relationships between two or more
passively observed variables. While the problem of such causal discovery has
been extensively studied especially in the bivariate setting, the majority of
current methods assume ...
We consider the problem of inferring causal relationships between two or more passively observed variables. Here, we propose a framework through which we can perform causal discovery in the presence of general non-linear relationships.

Published At:
2020-06-12

Tasks: Causal Discovery

Authors: Ricardo Pio Monti, Kun Zhang, Aapo Hyvarinen

Tasks: Causal Discovery

Authors: Ricardo Pio Monti, Kun Zhang, Aapo Hyvarinen

*
*
Discovery of causal relations from observational data is essential for many
disciplines of science and real-world applications. However, unlike other
machine learning algorithms, whose development has been greatly fostered by a
large amount of available ...
Discovery of causal relations from observational data is essential for many disciplines of science and real-world applications. As a clear advantage, the simulator can produce infinite samples without jeopardizing the privacy of real-world patients.

Published At:
2020-06-12

Tasks: Causal Discovery

4 starred

Authors: Kun Zhang, Ruibo Tu, Bo Christer Bertilson, Hedvig Kjellström, Cheng Zhang

Tasks: Causal Discovery

4 starred

Authors: Kun Zhang, Ruibo Tu, Bo Christer Bertilson, Hedvig Kjellström, Cheng Zhang

*
*
We consider the problem of learning causal relationships from relational
data. Existing approaches rely on queries to a relational conditional
independence (RCI) oracle to establish and orient causal relations in such a
setting. In practice, queries to a ...
We consider the problem of learning causal relationships from relational data. Existing approaches rely on queries to a relational conditional independence (RCI) oracle to establish and orient causal relations in such a setting.

*
*
While feedback loops are known to play important roles in many complex
systems (for example, in economical, biological, chemical, physical, control
and climatological systems), their existence is ignored in most of the causal
discovery literature, where ...
While feedback loops are known to play important roles in many complex systems (for example, in economical, biological, chemical, physical, control and climatological systems), their existence is ignored in most of the causal discovery literature, where systems are typically assumed to be acyclic from the outset. More specifically, we prove that for observational data generated by a simple and $\sigma$-faithful Structural Causal Model (SCM), FCI can be used to consistently estimate (i) the presence and absence of causal relations, (ii) the presence and absence of direct causal relations, (iii) the absence of confounders, and (iv) the absence of specific cycles in the causal graph of the SCM.

Published At:
2020-06-12

Tasks: Causal Inference, Causal Discovery

Authors: Joris M. Mooij, Tom Claassen

Tasks: Causal Inference, Causal Discovery

Authors: Joris M. Mooij, Tom Claassen

*
*
How can we enable machines to make sense of the world, and become better at
learning? To approach this goal, I believe viewing intelligence in terms of
many integral aspects, and also a universal two-term tradeoff between task
performance and complexity, ...
How can we enable machines to make sense of the world, and become better at learning? In this thesis, I address several key questions in some aspects of intelligence, and study the phase transitions in the two-term tradeoff, using strategies and tools from physics and information. In the information bottleneck, we theoretically show that these phase transitions are predictable and reveal structure in the relationships between the data, the model, the learned representation and the loss landscape.

Published At:
2020-06-12

Tasks: Representation Learning, Time Series, Causal Discovery, Few-Shot Learning

Authors: Tailin Wu

Tasks: Representation Learning, Time Series, Causal Discovery, Few-Shot Learning

Authors: Tailin Wu

*
*
We present Causal Generative Neural Networks (CGNNs) to learn functional
causal models from observational data. CGNNs leverage conditional
independencies and distributional asymmetries to discover bivariate and
multivariate causal structures. CGNNs make no ...
We present Causal Generative Neural Networks (CGNNs) to learn functional causal models from observational data. CGNNs make no assumption regarding the lack of confounders, and learn a differentiable generative model of the data by using backpropagation.

Published At:
2020-06-12

Tasks: Causal Discovery

Authors: Michele Sebag, Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz

Tasks: Causal Discovery

Authors: Michele Sebag, Olivier Goudet, Diviyan Kalainathan, Philippe Caillou, Isabelle Guyon, David Lopez-Paz

*
*
Many real datasets contain values missing not at random (MNAR). In this
scenario, investigators often perform list-wise deletion, or delete samples
with any missing values, before applying causal discovery algorithms. List-wise
deletion is a sound and ...
Many real datasets contain values missing not at random (MNAR). Our theoretical results show that test-wise deletion is sound under the justifiable assumption that none of the missingness mechanisms causally affect each other in the underlying causal graph.

Published At:
2020-06-12

Tasks: Causal Inference, Causal Discovery, Imputation

Authors: Eric V. Strobl, Shyam Visweswaran, Peter L. Spirtes

Tasks: Causal Inference, Causal Discovery, Imputation

Authors: Eric V. Strobl, Shyam Visweswaran, Peter L. Spirtes

*
*
Despite their popularity, many questions about the algebraic constraints
imposed by linear structural equation models remain open problems. For causal
discovery, two of these problems are especially important: the enumeration of
the constraints imposed by ...
Despite their popularity, many questions about the algebraic constraints imposed by linear structural equation models remain open problems. We show how the half-trek criterion can be used to make progress in both of these problems.

Published At:
2020-06-12

Tasks: Model Selection, Causal Discovery

4 starred

Authors: Joris M. Mooij, Thijs Van Ommen

Tasks: Model Selection, Causal Discovery

4 starred

Authors: Joris M. Mooij, Thijs Van Ommen

*
*
Discovering the causal structure among a set of variables is a fundamental
problem in many areas of science. In this paper, we propose Kernel Conditional
Deviance for Causal Inference (KCDC) a fully nonparametric causal discovery
method based on purely ...
Discovering the causal structure among a set of variables is a fundamental problem in many areas of science. Furthermore, we test our method on real-world time series data and the real-world benchmark dataset Tubingen Cause-Effect Pairs where we outperform existing state-of-the-art methods.

Published At:
2020-06-12

Tasks: Time Series, Causal Inference, Causal Discovery

Authors: Yee Whye Teh, Dino Sejdinovic, Jovana Mitrovic

Tasks: Time Series, Causal Inference, Causal Discovery

Authors: Yee Whye Teh, Dino Sejdinovic, Jovana Mitrovic

*
*
This paper frames causal structure estimation as a machine learning task. The
idea is to treat indicators of causal relationships between variables as
`labels' and to exploit available data on the variables of interest to provide
features for the labelling ...
This paper frames causal structure estimation as a machine learning task. We present empirical results on three different biological data sets (including examples where causal effects can be verified by experimental intervention), that together demonstrate the efficacy and general nature of the approach as well as its simplicity from a user's point of view.

Published At:
2020-06-12

Tasks: Causal Discovery

2 starred

Authors: Sach Mukherjee, Steven M. Hill, Chris. J. Oates, Duncan A. Blythe

Tasks: Causal Discovery

2 starred

Authors: Sach Mukherjee, Steven M. Hill, Chris. J. Oates, Duncan A. Blythe

*
*
In causal settings, such as instrumental variable settings, it is well known
that estimators based on ordinary least squares (OLS) can yield biased and
non-consistent estimates of the causal parameters. This is partially overcome
by two-stage least squares ...
In causal settings, such as instrumental variable settings, it is well known that estimators based on ordinary least squares (OLS) can yield biased and non-consistent estimates of the causal parameters. Establishing this connection comes with two benefits: (1) It enables us to prove robustness properties for existing K-class estimators when considering distributional shifts.

*
*
Causal discovery from a set of observations is one of the fundamental problems across several disciplines. For continuous variables, recently a number of causal discovery methods have demonstrated their effectiveness in distinguishing the cause from effect ...
Causal discovery from a set of observations is one of the fundamental problems across several disciplines.

Published At:
2020-06-12

Tasks: Causal Discovery

Authors: Kun Zhang, Ruichu Cai, Zhenjie Zhang, Zhifeng Hao, Jie Qiao

Tasks: Causal Discovery

Authors: Kun Zhang, Ruichu Cai, Zhenjie Zhang, Zhifeng Hao, Jie Qiao

*
*
The gold standard for discovering causal relations is by means of
experimentation. Over the last decades, alternative methods have been proposed
that can infer causal relations between variables from certain statistical
patterns in purely observational ...
The gold standard for discovering causal relations is by means of experimentation. Over the last decades, alternative methods have been proposed that can infer causal relations between variables from certain statistical patterns in purely observational data.

Published At:
2020-06-12

Tasks: Causal Inference, Causal Discovery

Authors: Joris M. Mooij, Tom Claassen, Sara Magliacane

Tasks: Causal Inference, Causal Discovery

Authors: Joris M. Mooij, Tom Claassen, Sara Magliacane

*
*
Measuring conditional independence is one of the important tasks in
statistical inference and is fundamental in causal discovery, feature
selection, dimensionality reduction, Bayesian network learning, and others. In
this work, we explore the connection ...
Measuring conditional independence is one of the important tasks in statistical inference and is fundamental in causal discovery, feature selection, dimensionality reduction, Bayesian network learning, and others. On the other hand, we also show that some popular---in machine learning---kernel conditional independence measures based on the Hilbert-Schmidt norm of a certain cross-conditional covariance operator, do not have a simple distance representation, except in some limiting cases.

Published At:
2020-06-12

Tasks: Dimensionality Reduction, Feature Selection, Causal Discovery

Authors: Bharath K. Sriperumbudur, Tianhong Sheng

Tasks: Dimensionality Reduction, Feature Selection, Causal Discovery

Authors: Bharath K. Sriperumbudur, Tianhong Sheng

*
*
Causal effect estimation from observational data is an important and much
studied research topic. The instrumental variable (IV) and local causal
discovery (LCD) patterns are canonical examples of settings where a closed-form
expression exists for the ...
Causal effect estimation from observational data is an important and much studied research topic. This brings about the paradoxical situation that, in the large-sample limit, no predictions are made, as detecting the weak edge invalidates the setting.

Published At:
2020-06-12

Tasks: Causal Discovery

Authors: Tom Heskes, Tom Claassen, Ioan Gabriel Bucur

Tasks: Causal Discovery

Authors: Tom Heskes, Tom Claassen, Ioan Gabriel Bucur

*
*
In this paper we present a comprehensive view of prominent causal discovery
algorithms, categorized into two main categories (1) assuming acyclic and no
latent variables, and (2) allowing both cycles and latent variables, along with
experimental results ...
In this paper we present a comprehensive view of prominent causal discovery algorithms, categorized into two main categories (1) assuming acyclic and no latent variables, and (2) allowing both cycles and latent variables, along with experimental results comparing them from three perspectives: (a) structural accuracy, (b) standard predictive accuracy, and (c) accuracy of counterfactual inference. For (b) and (c) we train causal Bayesian networks with structures as predicted by each causal discovery technique to carry out counterfactual or standard predictive inference.

Published At:
2020-06-12

Tasks: Causal Discovery, Counterfactual Inference

Authors: Gautam Shroff, Karamjit Singh, Garima Gupta, Vartika Tewari

Tasks: Causal Discovery, Counterfactual Inference

Authors: Gautam Shroff, Karamjit Singh, Garima Gupta, Vartika Tewari

*
*
Inferring a cause from its effect using observed time series data is a major
challenge in natural and social sciences. Assuming the effect is generated by
the cause trough a linear system, we propose a new approach based on the
hypothesis that nature ...
Inferring a cause from its effect using observed time series data is a major challenge in natural and social sciences. Assuming the effect is generated by the cause trough a linear system, we propose a new approach based on the hypothesis that nature chooses the "cause" and the "mechanism that generates the effect from the cause" independent of each other.

Published At:
2020-06-12

Tasks: Time Series, Causal Inference, Causal Discovery

Authors: Dominik Janzing, Naji Shajarisales, Bernhard Shoelkopf, Michel Besserve

Tasks: Time Series, Causal Inference, Causal Discovery

Authors: Dominik Janzing, Naji Shajarisales, Bernhard Shoelkopf, Michel Besserve

*
*
Knowledge bases (KB) constructed through information extraction from text
play an important role in query answering and reasoning. In this work, we study
a particular reasoning task, the problem of discovering causal relationships
between entities, known ...
Knowledge bases (KB) constructed through information extraction from text play an important role in query answering and reasoning. We introduce a probabilistic method for fusing noisy extractions with observational data to discover causal knowledge.

*
*
As systems are getting more autonomous with the development of artificial
intelligence, it is important to discover the causal knowledge from
observational sensory inputs. By encoding a series of cause-effect relations
between events, causal networks can ...
As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. Through extensive simulations on both synthetic and real data, we show that ICL can outperform state-of-the-art methods under different missing data mechanisms.

Published At:
2020-06-13

Tasks: Causal Discovery, Imputation

Authors: Hao Wang, Mykola Pechenizkiy, Vlado Menkovski, Xin Du, Yuhao Wang

Tasks: Causal Discovery, Imputation

Authors: Hao Wang, Mykola Pechenizkiy, Vlado Menkovski, Xin Du, Yuhao Wang

*
*
Discovering causal models from observational and interventional data is an
important first step preceding what-if analysis or counterfactual reasoning. As
has been shown before, the direction of pairwise causal relations can, under
certain conditions, be ...
Discovering causal models from observational and interventional data is an important first step preceding what-if analysis or counterfactual reasoning. Further, we observe that when less training data is available, our approach performs better than the GBC based approach suggesting that CNN models pre-trained to determine the direction of pairwise causal direction could have wider applicability in causal discovery and enabling what-if or counterfactual analysis.

Published At:
2020-06-13

Tasks: Causal Discovery

Authors: Gautam Shroff, Puneet Agarwal, Lovekesh Vig, Karamjit Singh, Garima Gupta

Tasks: Causal Discovery

Authors: Gautam Shroff, Puneet Agarwal, Lovekesh Vig, Karamjit Singh, Garima Gupta