Causal Discovery and Deep Learning #30

In this meetup, Gonçalo Faria argues that some of the hard open problems of Machine Learning and AI are intrinsically related to causality. Then, he'll explain fundamental concepts of causality and causal discovery and elaborate on the identifiability issues inherent to causal discovery with observational data. An approach to tackling these issues, in many circumstances, is considering latent interventions.

Gonçalo will present joint work with André Martins and Mário Figueiredo, where they design a causal discovery method for this scenario using neural networks and variational inference.

Speaker:
Gonçalo Faria is the Lead Machine Learning Engineer at dotmoovs. He has a BSc degree in CS from Minho University and recently graduated with a master’s in Data Science and Engineering from IST. His dissertation, “Differentiable Causal Discovery Under Latent Intervention”, which focused on causal discovery, received maximum grade and the Luis Vidigal award. The dissertation originated a scientific paper with the same name, co-authored by his advisors André Martins and Mário Figueiredo, presented at the 1st Conference on Causal Learning and Reasoning in California in April 2022. His main areas of research/interest are Causal Representation Learning, Causal Discovery, Generative Modeling, and Approximate Bayesian methods.

Meetup info:
As always, expect up to 1h of talk, with around 10 minutes in the end for the Q&A (be sure to leave all the questions you might have during the talk on the YouTube chat!).

The presentation content will be available on our GitHub page. The video will be streamed and saved on our Youtube page. You'll also be able to see this meetup's streaming link after registering for the event.

We hope that you'll join us!