| ΘΕΜΑ: Αναβολή ομιλίας: Υπενθύμιση: IACM Colloquium (Hybrid mode) - Sofia Triantafillou , 15:00 March 31 ΑΠΟΣΤΟΛΕΑΣ: Katerina Papadoulaki <kpapad@xxxxxx> η ομιλία αναβάλλεται για την επόμενη Πέμπτη 7/4/22 την ίδια ώρα  Title:  Learning treatment effects from observational and experimental data.  Speaker:  Prof. Sofia Triantafillou  Abstract:  Much of intelligent behavior involves predicting the causal effects of  actions. Observational data are plentiful in many domains, such as  electronic health record (EHR) data in the healthcare domain.  However, the use of observational data to estimate causal effects may  produce highly biased estimates. Experimental data, such as randomized  controlled trials (RCTs) in healthcare, provide relatively unbiased  estimates of causal effects, but are much scarcer. This talk will  describe a method that uses experimental data to determine whether and  how to use observational data to estimate causal effects. One  potential application of the method is personalized patient-outcome  prediction from EHR and RCT data.  Short Bio:  Sofia Triantafillou is an Assistant Professor in the Department of  Mathematics and Applied Mathematics in the University of Crete.  She has studied Applied Mathematics at NTUA and has a PhD in Computer  Science from the University of Crete. Before joining the University of  Crete, she was an Assistant Professor in the University of Pittsburgh.  Her research involves causal discovery and inference from multiple  sources of data, and applications of causal inference. She is  currently working on tuning causal discovery algorithms, and on  integrating observational and experimental data to improve causal  effect estimation.  Time, Date & Location:  15:00, Thursday 31st March 2022 @ Seminar Room 1 (max capacity: 34)  (main building)  Zoom Info:  IACM FORTH is inviting you to a scheduled Zoom meeting.  Topic: IACM FORTH Seminar's Zoom Meeting  Time: Mar 31, 2022 03:00 PM Athens  Join Zoom Meeting  https://zoom.us/j/7761040361?pwd=dEs4TFZxck01Vk5PQWR1TUxKdndwUT09  Meeting ID: 776 104 0361  Passcode: 787479 |