Towards causal machine learning

Register to ensure your place to hear Prof. Dr. Bernhard Schölkopf give the Microsoft Distinguished Research Lecture on 15 May.

 

Time: 16:45-17:45
Date: Friday 15 May 2015
Venue: Microsoft Research, 21 Station Road, Cambridge CB1 2FB

Prof. Dr. Bernhard Schölkopf writes:

In machine learning, we use data to automatically find dependences in the world, with the goal of predicting future observations. Most machine learning methods build on statistics, but one can also try to go beyond this, assaying causal structures underlying statistical dependences. Can such causal knowledge help prediction in machine learning tasks? We argue that this is indeed the case, due to the fact that causal models are more robust to changes that occur in real world datasets. We touch upon the implications of causal models for machine learning tasks such as domain adaptation, transfer learning, and semi-supervised learning. We also present an application to the removal of systematic errors for the purpose of exoplanet detection.

Machine learning currently mainly focuses on relatively well-studied statistical methods. Some of the causal problems are conceptually harder, however, the causal point of view can provide additional insights that have substantial potential for data analysis.

Please contact Emma Neave for more information.



Read more

Looking for something specific?