Randomized Experimental Design for Causal Graph Discovery
نویسندگان
چکیده
We examine the number of controlled experiments required to discover a causal graph. Hauser and Buhlmann [1] showed that the number of experiments required is logarithmic in the cardinality of maximum undirected clique in the essential graph. Their lower bounds, however, assume that the experiment designer cannot use randomization in selecting the experiments. We show that significant improvements are possible with the aid of randomization – in an adversarial (worst-case) setting, the designer can then recover the causal graph using at most O(log log n) experiments in expectation. This bound cannot be improved; we show it is tight for some causal graphs. We then show that in a non-adversarial (average-case) setting, even larger improvements are possible: if the causal graph is chosen uniformly at random under a Erdös-Rényi model then the expected number of experiments to discover the causal graph is constant. Finally, we present computer simulations to complement our theoretic results. Our work exploits a structural characterization of essential graphs by Andersson et al. [2]. Their characterization is based upon a set of orientation forcing operations. Our results show a distinction between which forcing operations are most important in worst-case and average-case settings.
منابع مشابه
Active Learning of Causal Networks with Intervention Experiments and Optimal Designs
The causal discovery from data is important for various scientific investigations. Because we cannot distinguish the different directed acyclic graphs (DAGs) in a Markov equivalence class learned from observational data, we have to collect further information on causal structures from experiments with external interventions. In this paper, we propose an active learning approach for discovering ...
متن کاملExperimental Design for Learning Causal Graphs with Latent Variables
We consider the problem of learning causal structures with latent variables using interventions. Our objective is not only to learn the causal graph between the observed variables, but to locate unobserved variables that could confound the relationship between observables. Our approach is stage-wise: We first learn the observable graph, i.e., the induced graph between observable variables. Next...
متن کاملCausal Graph Factored Joint Distribution Age
The literature on causal discovery has focused on interventions that involve randomly assigning values to a single variable. But such a randomized intervention is not the only possibility, nor is it always optimal. In some cases it is impossible or it would be unethical to perform such an intervention. We provide an account of “hard” and “soft” interventions, and discuss what they can contribut...
متن کاملCausation and Intervention
Accounts of causal discovery have traditionally split into approaches based on passive observational data and approaches based on experimental interventions that take control of (the distribution of) one or more variables. The former includes a vast number of techniques for the inference to causal structure on the basis of statistical features of data, while the latter provides in addition a me...
متن کاملExperimental Indistinguishability of Causal Structures
Using a variety of different results from the literature, I show how causal discovery with experiments is limited unless substantive assumptions about the underlying causal structure are made. These results undermine the view that experiments, such as randomized controlled trials, can independently provide a gold standard for causal discovery. Moreover, I present a concrete example in which cau...
متن کامل