Towards a Learning Theory of Cause-Effect Inference

By David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, Ilya O. Tolstikhin. 2015

184 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Causal Inference & Discovery

Citations in the corpus

Toward Causal Representation Learning (2021, background): “On the other hand, although methods for learning causal structure from observations exist [18], [37], [83], [113], [123], [139], [161], [174]–[176], [188]–[190], [229], [237], [246], [279], learning causal relations frequently requires collecting data from multiple environments or the ability to per”
Kernel Mean Embedding of Distributions: A Review and Beyonds (2016, methodology): “For example, Lopez-Paz et al. (2015) proposes to solve a bivariate cause-effect inference between RVs X and Y as a classification problem on µP(X,Y ) approximated with random Fourier features Rahimi and Recht (2007).”
Discovering Causal Signals in Images (2016, methodology): “To learn causal footprints from data, we follow [18] and pose cause-effect inference as a binary classification task.”
Towards Causal Representation Learning (2021, background): “[237, 188, 229, 113, 174, 187, 139, 17, 246, 277, 175, 123, 186, 176, 36, 82, 161], learning causal relations frequently requires collecting data from multiple environments, or the ability to perform interventions [251].”
On the Binding Problem in Artificial Neural Networks (2020, background): “We note that the problem of inferring structure has also received considerable attention in the causality literature, often specifically focusing on cause-effect discovery (e.g. see Hoyer et al. (2009); Lopez-Paz et al. (2015); Peters et al. (2016) or Peters et al. (2017) for an overview).”
Causality for Machine Learning (2019, positive): “…of methods that can detect causal direction better than chance (Mooij et al., 2016), some of them building on the above Kolmogorov complexity model (Budhathoki and Vreeken, 2016), and some directly learning to classify bivariate distributions into causal vs. anticausal (Lopez-Paz et al., 2015).”
Learning Neural Causal Models from Unknown Interventions (2019, neutral): “Learning based methods have been proposed (Guyon, a;b; Lopez-Paz et al., 2015) and there also exist recent approaches using the generalization ability of neural networks to learn causal signals from purely observational data (Kalainathan et al.”
Causal Regularization (2019, background): “Note that the type of causal learning learning theory developed here should not be confused with [23], which considers the generalization error of classifiers that infer cause-effect directions after being trained with multiple data sets of cause-effect pairs.”
Causal Generative Neural Networks (2017, background): “, 2012], or a large corpus of annotated causal relations [Lopez-Paz et al., 2015; Fonollosa, 2016].”
Minimax Estimation of Kernel Mean Embeddings (2016, methodology): “…et al., 2008; Fukumizu et al., 2008), covariate-shift (Smola et al., 2007), density estimation (Sriperumbudur, 2011), feature selection (Song et al., 2012), causal inference (Lopez-Paz et al., 2015), kernel Bayes’ rule (Fukumizu et al., 2013) and distribution regression (Szabó et al., 2015).”
Optimal Rates for Random Fourier Features (2015, background): “We also propose a RFF approximation to derivatives of a kernel with a theoretical study on its approximation quality.”
Computing functions of random variables via reproducing kernel Hilbert space representations (2015, neutral): “One can show that μ [ ˆ p m ] converges at rate m − 1 / 2 [cf. Smola et al. (2007), (Song 2008, Theorem 27), and Lopez-Paz et al. (2015)]: Independent of the requirement of injectivity, μ can be used to compute expectations of arbitrary functions f living in the RKHS, using the identity which…”
Revisiting Classifier Two-Sample Tests (2016, methodology): “re when applied to the 99 Tubingen cause-effect¨ pairs dataset, version August 2016 (Mooij et al., 2016). RCC is the Randomized Causation Coefﬁcient 9 Published as a conference paper at ICLR 2017 of (Lopez-Paz et al., 2015). The Ensemble-CGAN-C2ST trains 100 CGANs, and decides the causal direction b”
Structural Agnostic Modeling: Adversarial Learning of Causal Graphs (2018, background): “riables. Examples are the Additive Noise Model or ANM (Hoyer et al., 2009); the Gaussian Process Inference causal model, or GPI (Stegle et al., 2010); or the Randomized Causation Coefﬁ- cient, (RCC) (Lopez-Paz et al., 2015). On the other hand, some of these algorithms are able to estimate the causal”
Causal Inference via Kernel Deviance Measures (2018, methodology): “However, as noted in [13], this approach quickly becomes rather cumbersome as the number of labels grows super-exponentially in the number of variables due to the rapid increase of the number of DAGs that can be constructed from d variables.”