IEOR-DRO Seminar Series: Econometrics and Machine Learning via the Lens of Neyman Orthogonality
Tuesday,
November 13, 2018
1:10 AM - 2:10 AM
Speaker: Vasilis Syrgkanis(Microsoft)
Title: Econometrics and Machine Learning via the Lens of Neyman Orthogonality
Abstract: Many statistical estimation problems that arise in economic applications and more generally in causal inference, require the estimation of nuisance quantities that are not the focus of the analyst but are simply aides to identify causal models from observational data. Examples include modeling the treatment policy when estimating treatment effects, modeling the pricing policy when estimating demand elasticity or modeling an opponent’s behavior when estimating the structural utility parameters in a game of incomplete information. I will give an overview of recent results that invoke and extend the principle of Neyman-orthogonality to develop estimation methods whose target parameter error is robust to errors in the estimation of the nuisance components of the model. This enables fast mean squared error rates and asymptotically valid confidence intervals, even when the nuisance components are fitted via arbitrary ML-based approaches. I will discuss applications in the estimation of heterogeneous treatment effects, estimation with missing data, estimation in games of incomplete information and offline policy learning.
Based on joint works with: Ilias Zadik, Lester Mackey, Denis Nekipelov, Vira Semenova, Victor Chernozhukov, Miruna Oprescu, Steven Wu
Title: Econometrics and Machine Learning via the Lens of Neyman Orthogonality
Abstract: Many statistical estimation problems that arise in economic applications and more generally in causal inference, require the estimation of nuisance quantities that are not the focus of the analyst but are simply aides to identify causal models from observational data. Examples include modeling the treatment policy when estimating treatment effects, modeling the pricing policy when estimating demand elasticity or modeling an opponent’s behavior when estimating the structural utility parameters in a game of incomplete information. I will give an overview of recent results that invoke and extend the principle of Neyman-orthogonality to develop estimation methods whose target parameter error is robust to errors in the estimation of the nuisance components of the model. This enables fast mean squared error rates and asymptotically valid confidence intervals, even when the nuisance components are fitted via arbitrary ML-based approaches. I will discuss applications in the estimation of heterogeneous treatment effects, estimation with missing data, estimation in games of incomplete information and offline policy learning.
Based on joint works with: Ilias Zadik, Lester Mackey, Denis Nekipelov, Vira Semenova, Victor Chernozhukov, Miruna Oprescu, Steven Wu
LOCATION:
← BACK TO EVENTS
- Morningside
- Lecture
- Engineering
- Students
- Faculty
- Staff
- IEOR-DRO
Date Navigation Widget
Getting to Columbia
Other Calendars
- Alumni Events
- Barnard College
- Columbia Business School
- Columbia College
- Committee on Global Thought
- Heyman Center
- Jewish Theological Seminary
- Miller Theatre
- School of Engineering & Applied Science
- School of Social Work
- Teachers College
Guests With Disabilities
- Columbia University makes every effort to accommodate individuals with disabilities. Please notify us if you need any assistance by contacting the event’s point person. Alternatively, the Office of Disability Services can be reached at 212.854.2388 and [email protected]. Thank you.