Corpus ID: 195820364

Invariant Risk Minimization

@article{Arjovsky2019InvariantRM,
  title={Invariant Risk Minimization},
  author={Mart{\'i}n Arjovsky and L{\'e}on Bottou and Ishaan Gulrajani and David Lopez-Paz},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.02893}
}
  • Martín Arjovsky, Léon Bottou, +1 author David Lopez-Paz
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • 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. 

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 79 CITATIONS

    Observational Overfitting in Reinforcement Learning

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Out-of-Distribution Generalization via Risk Extrapolation (REx)

    VIEW 20 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    ENTROPY PENALTY: TOWARDS GENERALIZATION BE-

    VIEW 7 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    ENTROPY PENALTY: TOWARDS GENERALIZATION BE-

    • YOND THE, IID ASSUMPTION
    • 2019
    VIEW 7 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Modular Meta-Learning with Shrinkage

    Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation

    VIEW 10 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    A Causal View on Robustness of Neural Networks

    VIEW 1 EXCERPT
    CITES METHODS

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 24 Highly Influenced Citations

    • Averaged 26 Citations per year from 2018 through 2020

    • 228% Increase in citations per year in 2020 over 2019

    References

    Publications referenced by this paper.