MMLL webinar series I: Causality

The Mercury Machine Learning Lab (MMLL) would like to invite you to the MMLL online seminar series. In this series of four webinars, the lab will focus on causality, information retrieval, natural language processing, and reinforcement learning.

The kick-off webinar on March 10, from 15-16.30hrs, will cover causality and is given by professor Juan D. Correa.

Program:
15.00: Introduction of the Mercury Machine Learning Lab lab by Dr. Onno Zoeter (Booking.com)

15.20: Prof. dr. Juan D. Correa (Universidad Autónoma de Manizales) presents “Generalization of Causal and Statistical Quantities under Transportability and Selection Bias”

16.00: Q&A

16.15: End

After registering, you will receive a confirmation email containing the information about joining the webinar. Register here

Abstract presentation

Title
“Generalization of Causal and Statistical Quantities under Transportability and Selection Bias”

Extrapolating data across domains is relevant in many data-driven disciplines, especially the empirical sciences and machine learning. This ability is indispensable for building systems robust to changing conditions in the environment. In this talk, we discuss “transportability” and “selection bias,” two common challenges for generalizing heterogeneous data to obtain a statistical or causal quantity of interest in a target domain. We discuss a graphical approach to model these problems representing the assumptions needed to derive conditions and algorithms to solve them in a nonparametric setting. These results allow us to find, if it exists, a function of the available data equal to the quantity of interest.

More info about this series:
Each event will last one hour, with a 5-minute intro by one of the lab representatives about the lab and its objectives, 40-minute talk by the keynote speaker, and a 15 minute Q&A session.

Other webinars are planned for the following dates:
March 31, 2022, 15:00-16:00 Prof. dr. Nikos Vlassis on reinforcement learning             

April 21, 2022, 15:00-16:00 Prof. dr. Mounia Lalmas on information retrieval                   

May 12, 2022, 15:00-16:00 (tbd) on natural language processing