2 code implementations • 17 Apr 2024 • Juan L. Gamella, Jonas Peters, Peter Bühlmann
The devices, which we call causal chambers, are computer-controlled laboratories that allow us to manipulate and measure an array of variables from these physical systems, providing a rich testbed for algorithms from a variety of fields.
no code implementations • 15 Apr 2024 • Margherita Lazzaretto, Jonas Peters, Niklas Pfister
We consider the task of predicting a response Y from a set of covariates X in settings where the conditional distribution of Y given X changes over time.
no code implementations • 9 Oct 2023 • Nicola Gnecco, Jonas Peters, Sebastian Engelke, Niklas Pfister
In particular, we establish a novel connection between the field of distribution generalization from machine learning, and simultaneous equation models and control function from econometrics.
no code implementations • 6 Oct 2023 • Sorawit Saengkyongam, Elan Rosenfeld, Pradeep Ravikumar, Niklas Pfister, Jonas Peters
In this paper, we consider the task of intervention extrapolation: predicting how interventions affect an outcome, even when those interventions are not observed at training time, and show that identifiable representations can provide an effective solution to this task even if the interventions affect the outcome non-linearly.
1 code implementation • 22 Sep 2023 • Lucas Kook, Sorawit Saengkyongam, Anton Rask Lundborg, Torsten Hothorn, Jonas Peters
Discovering causal relationships from observational data is a fundamental yet challenging task.
no code implementations • 19 Jun 2023 • Sorawit Saengkyongam, Niklas Pfister, Predrag Klasnja, Susan Murphy, Jonas Peters
A major challenge in policy learning is how to adapt efficiently to unseen environments or tasks.
1 code implementation • 1 Jun 2023 • Frederik Hytting Jørgensen, Sebastian Weichwald, Jonas Peters
Many fairness criteria constrain the policy or choice of predictors.
no code implementations • 17 Mar 2022 • Niklas Pfister, Jonas Peters
Exogenous heterogeneity, for example, in the form of instrumental variables can help us learn a system's underlying causal structure and predict the outcome of unseen intervention experiments.
1 code implementation • 11 Mar 2022 • Nikolaj Thams, Rikke Søndergaard, Sebastian Weichwald, Jonas Peters
In this paper, we outline the difficulties that arise due to time structure and propose methodology for constructing identifying equations that can be used for consistent parametric estimation of causal effects in time series data.
1 code implementation • 12 Feb 2022 • Sebastian Weichwald, Søren Wengel Mogensen, Tabitha Edith Lee, Dominik Baumann, Oliver Kroemer, Isabelle Guyon, Sebastian Trimpe, Jonas Peters, Niklas Pfister
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i. i. d.
Model-based Reinforcement Learning reinforcement-learning +1
1 code implementation • 3 Feb 2022 • Sorawit Saengkyongam, Leonard Henckel, Niklas Pfister, Jonas Peters
Most of the existing estimators assume that the error term in the response $Y$ and the hidden confounders are uncorrelated with the instruments $Z$.
1 code implementation • 2 Feb 2022 • Phillip B. Mogensen, Nikolaj Thams, Jonas Peters
Recently, methods have been proposed that exploit the invariance of prediction models with respect to changing environments to infer subsets of the causal parents of a response variable.
1 code implementation • 19 Aug 2021 • Martin Emil Jakobsen, Rajen D. Shah, Peter Bühlmann, Jonas Peters
Furthermore, we study the identifiability gap, which quantifies how much better the true causal model fits the observational distribution, and prove that it is lower bounded by local properties of the causal model.
1 code implementation • 1 Jun 2021 • Sorawit Saengkyongam, Nikolaj Thams, Jonas Peters, Niklas Pfister
We adopt the concept of invariance from the causality literature and introduce the notion of policy invariance.
1 code implementation • 3 Mar 2021 • Michael Oberst, Nikolaj Thams, Jonas Peters, David Sontag
In the case of two proxy variables, we propose a modified estimator that is prediction optimal under interventions up to a known strength.
no code implementations • 18 Jan 2021 • Anton Rask Lundborg, Rajen D. Shah, Jonas Peters
We study the problem of testing the null hypothesis that X and Y are conditionally independent given Z, where each of X, Y and Z may be functional random variables.
Statistics Theory Statistics Theory
1 code implementation • 12 Jun 2020 • Rune Christiansen, Niklas Pfister, Martin Emil Jakobsen, Nicola Gnecco, Jonas Peters
We introduce the formal framework of distribution generalization that allows us to analyze the above problem in partially observed nonlinear models for both direct interventions on $X$ and interventions that occur indirectly via exogenous variables $A$.
Methodology Primary 62Gxx, secondary 62G35, 62G08, 62D20
1 code implementation • 7 May 2020 • Martin Emil Jakobsen, Jonas Peters
While causal models are robust in that they are prediction optimal under arbitrarily strong interventions, they may not be optimal when the interventions are bounded.
no code implementations • 14 Feb 2020 • Sebastian Weichwald, Jonas Peters
Robustness (or invariance) is a fundamental principle underlying causal methodology.
no code implementations • 17 Jan 2020 • Jonas Peters, Stefan Bauer, Niklas Pfister
In this chapter, we provide a natural and straight-forward extension of this concept to dynamical systems, focusing on continuous time models.
Methodology Dynamical Systems
1 code implementation • 5 Nov 2019 • Niklas Pfister, Evan G. Williams, Jonas Peters, Ruedi Aebersold, Peter Bühlmann
In particular, it is useful to distinguish between stable and unstable predictors, i. e., predictors which have a fixed or a changing functional dependence on the response, respectively.
Methodology Applications
2 code implementations • 14 Aug 2019 • Nicola Gnecco, Nicolai Meinshausen, Jonas Peters, Sebastian Engelke
Causal questions are omnipresent in many scientific problems.
Methodology
no code implementations • 28 Oct 2018 • Niklas Pfister, Stefan Bauer, Jonas Peters
Results on both simulated and real-world examples suggest that learning the structure of kinetic systems benefits from a causal perspective.
2 code implementations • 18 Jan 2018 • Dominik Rothenhäusler, Nicolai Meinshausen, Peter Bühlmann, Jonas Peters
If anchor regression and least squares provide the same answer (anchor stability), we establish that OLS parameters are invariant under certain distributional changes.
Methodology
1 code implementation • 26 Jun 2017 • Christina Heinze-Deml, Jonas Peters, Nicolai Meinshausen
In this work, we present and evaluate an array of methods for nonlinear and nonparametric versions of ICP for learning the causal parents of given target variables.
Methodology
no code implementations • 18 Nov 2016 • Stephan Bongers, Patrick Forré, Jonas Peters, Joris M. Mooij
In this paper, we investigate SCMs in a more general setting, allowing for the presence of both latent confounders and cycles.
no code implementations • 1 Mar 2016 • Niklas Pfister, Peter Bühlmann, Bernhard Schölkopf, Jonas Peters
Based on an empirical estimate of dHSIC, we define three different non-parametric hypothesis tests: a permutation test, a bootstrap test and a test based on a Gamma approximation.
1 code implementation • 19 Jul 2015 • Mateo Rojas-Carulla, Bernhard Schölkopf, Richard Turner, Jonas Peters
We focus on the problem of Domain Generalization, in which no examples from the test task are observed.
1 code implementation • NeurIPS 2015 • Dominik Rothenhäusler, Christina Heinze, Jonas Peters, Nicolai Meinshausen
We propose a simple method to learn linear causal cyclic models in the presence of latent variables.
1 code implementation • 12 May 2015 • Bernhard Schölkopf, David W. Hogg, Dun Wang, Daniel Foreman-Mackey, Dominik Janzing, Carl-Johann Simon-Gabriel, Jonas Peters
We describe a method for removing the effect of confounders in order to reconstruct a latent quantity of interest.
no code implementations • 27 Jan 2015 • Bernhard Schölkopf, Krikamol Muandet, Kenji Fukumizu, Jonas Peters
We describe a method to perform functional operations on probability distributions of random variables.
no code implementations • 6 Jan 2015 • Jonas Peters, Peter Bühlmann, Nicolai Meinshausen
In contrast, predictions from a non-causal model can potentially be very wrong if we actively intervene on variables.
Methodology
no code implementations • 11 Dec 2014 • Joris M. Mooij, Jonas Peters, Dominik Janzing, Jakob Zscheischler, Bernhard Schölkopf
We evaluate the performance of several bivariate causal discovery methods on these real-world benchmark data and in addition on artificially simulated data.
no code implementations • 3 Mar 2014 • Jonas Peters
This work investigates the intersection property of conditional independence.
no code implementations • NeurIPS 2013 • Jonas Peters, Dominik Janzing, Bernhard Schölkopf
We study a class of restricted Structural Equation Models for time series that we call Time Series Models with Independent Noise (TiMINo).
no code implementations • 6 Oct 2013 • Peter Bühlmann, Jonas Peters, Jan Ernest
We develop estimation for potentially high-dimensional additive structural equation models.
no code implementations • 26 Sep 2013 • Eleni Sgouritsa, Dominik Janzing, Jonas Peters, Bernhard Schoelkopf
We propose a kernel method to identify finite mixtures of nonparametric product distributions.
no code implementations • 26 Sep 2013 • Jonas Peters, Joris Mooij, Dominik Janzing, Bernhard Schölkopf
We consider the problem of learning causal directed acyclic graphs from an observational joint distribution.
4 code implementations • 5 Jun 2013 • Jonas Peters, Peter Bühlmann
To quantify such differences, we propose a (pre-) distance between DAGs, the structural intervention distance (SID).
no code implementations • 11 Sep 2012 • Léon Bottou, Jonas Peters, Joaquin Quiñonero-Candela, Denis X. Charles, D. Max Chickering, Elon Portugaly, Dipankar Ray, Patrice Simard, Ed Snelson
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 to the system.
1 code implementation • 27 Jun 2012 • Bernhard Schoelkopf, Dominik Janzing, Jonas Peters, Eleni Sgouritsa, Kun Zhang, Joris Mooij
We consider the problem of function estimation in the case where an underlying causal model can be inferred.
no code implementations • 11 May 2012 • Jonas Peters, Peter Bühlmann
In this work, we prove full identifiability if all noise variables have the same variances: the directed acyclic graph can be recovered from the joint Gaussian distribution.
2 code implementations • 14 Feb 2012 • Kun Zhang, Jonas Peters, Dominik Janzing, Bernhard Schoelkopf
Conditional independence testing is an important problem, especially in Bayesian network learning and causal discovery.
no code implementations • NeurIPS 2008 • Patrik O. Hoyer, Dominik Janzing, Joris M. Mooij, Jonas Peters, Bernhard Schölkopf
The discovery of causal relationships between a set of observed variables is a fundamental problem in science.