Causal Inference as Computational Learning

Judea Pearl, University of California Los Angeles, USA

The traditional aim of machine learning methods is to infer meaningful features of an underlying probability distribution from samples drawn from that distribution. With the help of such features, one can predict relationships in yet unobserved samples, and infer the likelihood of past and future events in light of new evidence. Causal analysis goes one step further; it aims at inferring features of the data-generating process, that is, of the invariant strategy by which Nature assigns values to the variables in the distribution. These deeper features enable us to predict, not merely relationships governed by the underlying distribution, but also how that distribution would CHANGE when conditions are altered, say, by deliberate interventions or by spontaneous transformations.
Although full description of the generating process cannot be learned from data alone, many useful features of the process can be learned from a combination of (1) data (2) prior qualitative knowledge and/or (3) experiments. Thus, the challenge of causal inference is to answer practical queries about the underlying process with minimum number of assumptions and with minimal experimentation. I will present theoretical and methodological results concerning the learnability of three types of queries: (1) queries about the effect of potential interventions, (2) queries about attribution (i.e., whether event x was necessary for the occurrence of event y) and (3) queries about the direct (or indirect) effect of one event on another.

For background information, see Causality (Pearl, 2000, Cambridge University Press), or the following papers:


Judea Pearl

Judea Pearl is a professor of computer science and statistics at the University of California, Los Angeles. He joined the faculty of UCLA in 1970, where he currently directs the Cognitive Systems Laboratory and conducts research in artificial intelligence, human reasoning and philosophy of science. He has authored three books: Heuristics (1984), Probabilistic Reasoning (1988), and Causality (2000). A member of the National Academy of Engineering, and a Founding Fellow the American Association for Artificial Intelligence (AAAI), Judea Pearl is the recipient of the IJCAI Research Excellence Award for 1999, the London School of Economics Lakatos Award for 2001 and the ACM Alan Newell Award for 2004. In April 2008, he received the Benjamin Franklin Medal for Computer and Cognitive Science from the Franklin Institute

NIPS 2008 workshop on causality