Inspiration Exchange: individualized treatment effect inference (first session)

The van der Schaar Lab’s eighth Inspiration Exchange session took place virtually on April 28, 2021, and was attended by students and professionals from the AI and machine learning community. This was the first of 3 planned sessions focusing on individualized treatment effect inference (ITE inference).

The former half of the session featured 2 presentations introducing individualized treatment effect inference. This was followed by a participative discussion in which members of the lab and session participants discussed several key topics related to ITE inference, ranging from the evaluation of models to working with different types of data, to potentially relaxing some of the typical assumptions related to ITE inference.

The next Inspiration Exchange session on ITE inference will take place on May 28. Details can be found here.

Introduction – 0:00​
Resources: overview on ITE inference – 2:27​
Resources: ITE inference video tutorial series – 2:59​
Presentation 1 [ITE inference: a machine learning approach // Mihaela van der Schaar] – 4:10​
Presentation 2 [Estimating effects of continuous-valued interventions with GANs // Ioana Bica] – 23:51​
Participative discussion: topic 1 [different ways to evaluate ITE models] – 35:10​
Participative discussion: topic 2 [estimating ITEs from clinical trials and observational data] – 50:48​
Participative discussion: topic 3 [relaxing typical ITE assumptions] – 59:29​
Intro to next sessions – 1:02:53

For more info related to our lab’s work on individualized treatment effect inference, please view our overview here, or our series of video tutorials here.

A full list of the lab’s publications can be found here.