Statistical Machine Learning Seminar
The 50th Statistical Machine Learning Seminar
Organized by the Research Center for Statistical Machine Learning, The Institute of Statistical Mathematics

The 50th Statistical Machine Learning Seminar

Date & Time: 16:00-17:30, September 27 (Tue) 
Place: Zoom
Speaker: Motonobu Kanagawa (EURECOM)
Title: Counterfactual Mean Embeddings

Abstract:
Counterfactual inference has become ubiquitous in online advertisement, recommendation systems, medical diagnosis, and econometrics. Accurate modeling of outcome distributions associated with different interventions—known as counterfactual distributions—is crucial for the success of these applications. We propose to model counterfactual distributions using a novel Hilbert space representation called counterfactual mean embedding (CME) in this work. The CME embeds the associated counterfactual distribution into a reproducing kernel Hilbert space (RKHS) endowed with a positive definite kernel, which allows us to perform causal inference over the entire landscape of the counterfactual distribution. Based on this representation, we propose a distributional treatment effect (DTE) that can quantify the causal effect over entire outcome distributions. Our approach is nonparametric as the CME can be estimated under the unconfoundedness assumption from observational data without requiring any parametric assumption about the underlying distributions. We also establish a rate of convergence of the proposed estimator which depends on the smoothness of the conditional mean and the Radon-Nikodym derivative of the underlying marginal distributions. Furthermore, our framework allows for more complex outcomes such as images, sequences, and graphs. Our experimental results on synthetic data and off-policy evaluation tasks demonstrate the advantages of the proposed estimator

 


Your Name *
Note: If you do not receive an email with the information of Zoom link, please check the email address by accessing this Google form.  If there is a problem, please contact fukumizu@ism.ac.jp.
Email Address (Zoom link will be emailed to this address.  Double check if it is correct.) *
Comments (if any)
Submit
Clear form
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy