• Computer Science, Mathematics
  • Published in ArXiv 2020

Invariant Risk Minimization Games

@article{Ahuja2020InvariantRM,
  title={Invariant Risk Minimization Games},
  author={Kartik Ahuja and Karthikeyan Shanmugam and Kush Varshney and Amit Dhurandhar},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04692}
}
The standard risk minimization paradigm of machine learning is brittle when operating in environments whose test distributions are different from the training distribution due to spurious correlations. Training on data from many environments and finding invariant predictors reduces the effect of spurious features by concentrating models on features that have a causal relationship with the outcome. In this work, we pose such invariant risk minimization as finding the Nash equilibrium of an… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 58 REFERENCES

and D

  • M. Arjovsky, L. Bottou, I. Gulrajani
  • Lopez-Paz, “Invariant risk minimization,” arXiv preprint arXiv:1907.02893
  • 2019
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

and Y

  • I. Goodfellow, J. Pouget-Abadie, +4 authors A. Courville
  • Bengio, “Generative adversarial nets,” in Advances in neural information processing systems
  • 2014
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

and L

  • Z. Lu, H. Pu, F. Wang, Z. Hu
  • Wang, “The expressive power of neural networks: A view from the width,” in Advances in neural information processing systems
  • 2017
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A Social Equilibrium Existence Theorem.

  • Gérard Debreu
  • Computer Science, Medicine
  • Proceedings of the National Academy of Sciences of the United States of America
  • 1952
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Causal Confusion in Imitation Learning

VIEW 1 EXCERPT

R

  • H. Zhao
  • T. d. Combes, K. Zhang, and G. J. Gordon, “On learning invariant representation for domain adaptation,” arXiv preprint arXiv:1901.09453
  • 2019
VIEW 1 EXCERPT