351 citations · 1.8k across the 37 of their papers we have counts for
9 papers · 1 filter
Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning
Sebastian Weichwald, Søren Wengel Mogensen, Tabitha Edith Lee +6
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider th…
Invariant Policy Learning: A Causal Perspective
Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters +1
Contextual bandit and reinforcement learning algorithms have been successfully used in various interactive learning systems such as online advertising, recommender systems, and dyn…
Regularizing towards Causal Invariance: Linear Models with Proxies
Michael Oberst, Nikolaj Thams, Jonas Peters +1
We propose a method for learning linear models whose predictive performance is robust to causal interventions on unobserved variables, when noisy proxies of those variables are ava…
Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders
Eleni Sgouritsa, Dominik Janzing, Jonas Peters +1
We propose a kernel method to identify finite mixtures of nonparametric product distributions. It is based on a Hilbert space embedding of the joint distribution. The rank of the c…
Counterfactual Reasoning and Learning Systems
Léon Bottou, Jonas Peters, Joaquin Quiñonero-Candela +6
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes t…
On Causal and Anticausal Learning
Bernhard Schoelkopf, Dominik Janzing, Jonas Peters +3
We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, co…
Kernel-based Conditional Independence Test and Application in Causal Discovery
Kun Zhang, Jonas Peters, Dominik Janzing +1
Conditional independence testing is an important problem, especially in Bayesian network learning and causal discovery. Due to the curse of dimensionality, testing for conditional…
Identifiability of Causal Graphs using Functional Models
Jonas Peters, Joris Mooij, Dominik Janzing +1
This work addresses the following question: Under what assumptions on the data generating process can one infer the causal graph from the joint distribution? The approach taken by…
Detecting low-complexity unobserved causes
Dominik Janzing, Eleni Sgouritsa, Oliver Stegle +2
We describe a method that infers whether statistical dependences between two observed variables X and Y are due to a "direct" causal link or only due to a connecting causal path th…