Research talk: Causal learning: Discovering causal relations for out-of-distribution generalization
Machine learning models should be explainable and robust on out-of-distribution samples, especially on safety-critical tasks such as healthcare, and security. However, current models heavily rely on i.i.d assumption, and are therefore sensitive to OOD data. In this talk, Wei Chen, from the Computing and Learning Theory group at Microsoft Research Asia, will show how causal inference tools can be leveraged to empower machine learning models and make them more robust. To achieve this goal, we propose the causal invariance model, which can eliminate spurious correlations and keep only causal relation for prediction, and we will show both theoretical and empirical proof.
Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit (opens in new tab)
- Track:
- Causal Machine Learning
- Date:
- Speakers:
- Wei Chen
- Affiliation:
- Microsoft Research
Causal Machine Learning
-
Opening remarks: Causal Machine Learning
Speakers:- Cheng Zhang
-
-
Research talk: Causal ML and business
Speakers:- Jacob LaRiviere
-
Research talk: Can causal learning improve the privacy of ML models?
Speakers:- Shruti Tople
-
-
Panel: Challenges and opportunities of causality
Speakers:- Eric Horvitz,
- Yoshua Bengio,
- Susan Athey
-
-
Research talk: Causal ML and fairness
Speakers:- Allison Koenecke
-
Panel: Causal ML Research at Microsoft
Speakers:- Adith Swaminathan,
- Javier González Hernández,
- Justin Ding
-
Research talk: Post-contextual-bandit inference
Speakers:- Nathan Kallus
-
-
Demo: Enabling end-to-end causal inference at scale
Speakers:- Eleanor Dillon,
- Amit Sharma
-
-
Panel: Causal ML in industry
Speakers:- Ya Xu,
- Totte Harinen,
- Dawen Liang
-
Closing remarks: Causal Machine Learning
Speakers:- Emre Kiciman
