EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3357. Source Condition Double Robust Inference on Functionals of Inverse Problems
Invited abstract in session TD-6: Advancements of OR-analytics in statistics, machine learning and data science 15, stream Advancements of OR-analytics in statistics, machine learning and data science.
Tuesday, 14:30-16:00Room: 1013 (building: 202)
Authors (first author is the speaker)
1. | Nathan Kallus
|
Cornell University |
Abstract
We consider estimation of parameters defined as linear functionals of solutions to linear inverse problems. Any such parameter admits a doubly robust representation that depends on the solution to a dual linear inverse problem, where the dual solution can be thought as a generalization of the inverse propensity function. We provide the first source condition double robust inference method that ensures asymptotic normality around the parameter of interest as long as either the primal or the dual inverse problem is sufficiently well-posed, without knowledge of which inverse problem is the more well-posed one. Our result is enabled by guarantees for novel iterated Tikhonov regularized adversarial minimax estimators based on minimax (robust) optimization over general hypothesis spaces.
Keywords
- Economic Modeling
- Robust Optimization
- Machine Learning
Status: accepted
Back to the list of papers