University of Cambridge > > Machine Learning Reading Group @ CUED > Causal Representation Learning

Causal Representation Learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Elre Oldewage.

In recent years, there is growing interest in integrating machine learning with causality, as both communities are realising that one can benefit from the advances of the other. In this talk, we first review fundamental concepts of causal inference in relation to key problems of machine learning to show how causality can contribute to machine learning. Then, since most work in causality is predicated on that causal variables are given, we discuss how to discover high-level causal variables from low-level observations by leveraging machine learning methods, which is a central problem for causality and AI. Finally, we showcase a series of recent work on designing practical algorithms to address this problem.

References: [1] Schölkopf et al. Towards Causal Representation Learning. 2021 [2] Peters et al. Causal Inference using Invariant Prediction: Identification and Confidence Intervals. 2015 [3] Arjovsky et al. Invariant Risk Minimization. 2019 [4] Lu et al. Nonlinear Invariant Risk Minimization: A Causal Approach. 2021

This talk is part of the Machine Learning Reading Group @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity