From Dependence to Causation

by   David Lopez-Paz, et al.

Machine learning is the science of discovering statistical dependencies in data, and the use of those dependencies to perform predictions. During the last decade, machine learning has made spectacular progress, surpassing human performance in complex tasks such as object recognition, car driving, and computer gaming. However, the central role of prediction in machine learning avoids progress towards general-purpose artificial intelligence. As one way forward, we argue that causal inference is a fundamental component of human intelligence, yet ignored by learning algorithms. Causal inference is the problem of uncovering the cause-effect relationships between the variables of a data generating system. Causal structures provide understanding about how these systems behave under changing, unseen environments. In turn, knowledge about these causal dynamics allows to answer "what if" questions, describing the potential responses of the system under hypothetical manipulations and interventions. Thus, understanding cause and effect is one step from machine learning towards machine reasoning and machine intelligence. But, currently available causal inference algorithms operate in specific regimes, and rely on assumptions that are difficult to verify in practice. This thesis advances the art of causal inference in three different ways. First, we develop a framework for the study of statistical dependence based on copulas and random features. Second, we build on this framework to interpret the problem of causal inference as the task of distribution classification, yielding a family of novel causal inference algorithms. Third, we discover causal structures in convolutional neural network features using our algorithms. The algorithms presented in this thesis are scalable, exhibit strong theoretical guarantees, and achieve state-of-the-art performance in a variety of real-world benchmarks.


page 1

page 2

page 3

page 4


Private Causal Inference

Causal inference deals with identifying which random variables "cause" o...

Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolution

Current machine learning systems operate, almost exclusively, in a stati...

Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments

Algorithm fairness has become a central problem for the broad adoption o...

Quantum Entropic Causal Inference

As quantum computing and networking nodes scale-up, important open quest...

Causal Inference in Geosciences with Kernel Sensitivity Maps

Establishing causal relations between random variables from observationa...

Who Make Drivers Stop? Towards Driver-centric Risk Assessment: Risk Object Identification via Causal Inference

We propose a framework based on causal inference for risk object identif...

The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data

Causal inference is central to many areas of artificial intelligence, in...

Please sign up or login with your details

Forgot password? Click here to reset