The Randomized Causation Coefficient

نویسندگان

  • David Lopez-Paz
  • Krikamol Muandet
  • Benjamin Recht
چکیده

We are interested in learning causal relationships between pairs of random variables, purely from observational data. To effectively address this task, the state-of-the-art relies on strong assumptions on the mechanisms mapping causes to effects, such as invertibility or the existence of additive noise, which only hold in limited situations. On the contrary, this short paper proposes to learn how to perform causal inference directly from data, without the need of feature engineering. In particular, we pose causality as a kernel mean embedding classification problem, where inputs are samples from arbitrary probability distributions on pairs of random variables, and labels are types of causal relationships. We validate the performance of our method on synthetic and real-world data against the state-of-the-art. Moreover, we submitted our algorithm to the ChaLearn’s “Fast Causation Coefficient Challenge” competition, with which we won the fastest code prize and ranked third in the overall leaderboard.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A causation coefficient and taxonomy of correlation/causation relationships

This paper introduces a causation coefficient which is defined in terms of probabilistic causal models. This coefficient is suggested as the natural causal analogue of the Pearson correlation coefficient and permits comparing causation and correlation to each other in a simple, yet rigorous manner. Together, these coefficients provide a natural way to classify the possible correlation/causation...

متن کامل

مفهوم علیت در پارادایم‌های پزشکی

In this article, we aim to discuss one of the essential concepts of medicine. As a rule, such studies attempt to clarify the philosophical principals of medicine, whereby the act of medic can be regulated based on his clear perceptions of the principles of his knowledge. In this article, we will evaluate the concept of causation in medicine from a philosophical point of view and through histor...

متن کامل

Factors of occupational injury: a survey in a chemical company.

Chemical industries being the seat of dangerous occurrences frequently resulting in injuries, an occupational injury surveillance study was initiated involving 307 permanent and 419 temporary workers in a chemical company to understand the contribution of different possible factors on injury causation. Risk calculation was undertaken in relation to every individual factor using univariate and m...

متن کامل

Thinking as Evidence for the Probability of the Existence of a God: An Argument from Unnaturalness for Necessity

The objective of this article is to show that it is justified to assert that the existence of God is plausible, considering the fact that thinking itself is an immediate outcome (effect) of a thinker (cause). This idea may seem evident, but it is in fact challenged by certain claims of cognitive philosophers who aver that our knowledge of necessity and causation is, i...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • Journal of Machine Learning Research

دوره 16  شماره 

صفحات  -

تاریخ انتشار 2015