Game-theoretic Formulation of Invariant Risk Minimization

ICML 2020

Game-theoretic Formulation of Invariant Risk Minimization

Jul 12, 2020
|
22 views
|
|
Code
Details
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top of that data representation, matches for all training distributions. Through theory and experiments, we show how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization. Speakers: Kartik Ahuja, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney

Comments
loading...