Frontiers in Machine Learning: Big Ideas in Causality and Machine Learning

Опубликовано 28 июля 2020, 20:07

Causal relationships are stable across distribution shifts. Models based on causal knowledge have the potential to generalize to unseen domains and offer counterfactual predictions: how do outcomes change if a certain feature is changed in the real world. In recent years, machine learning methods based on causal reasoning have led to advances in out-of-domain generalization, fairness and explanation, and robustness to data selection biases. ¬ In this session, we discuss big ideas at the intersections of causal inference and machine learning towards building stable predictive models and discovering causal insights from data.

Special MSR India session

Session Lead: Amit Sharma, Microsoft

Speaker: Susan Athey, Stanford University
Talk Title: Causal Inference, Consumer Choice, and the Value of Data

Speaker: Elias Bareinboim, Columbia University
Talk Title: On the Causal Foundations of Artificial Intelligence (Explainability & Decision-Making)

Speaker: Cheng Zhang, Microsoft
Talk Title: A causal view on Robustness of Neural Networks

Q&A panel with all 3 speakers

See more on-demand sessions from Microsoft Research's Frontiers in Machine Learning 2020 virtual event: microsoft.com/en-us/research/e...