/jax_ood

Jax implementation of OOD approaches

Primary LanguagePythonOtherNOASSERTION

Introduction

Re-implementing the original code for Jax/Haiku. Jax is considered to be the fastest deep learning framework at this time. Reimplementing OOD algorithms has the benefit of faster training/inference, plus, the implementation is personally a way for me to learn in detail how the algorithms are implemented.

Further improvements to OOD approaches will be branched using this code as the base.

-- Anique

Original Code repository for Invariant Risk Minimization

Source code for the paper:

@article{InvariantRiskMinimization,
    title={Invariant Risk Minimization},
    author={Arjovsky, Martin and Bottou, L{\'e}on and Gulrajani, Ishaan and Lopez-Paz, David},
    journal={arXiv},
    year={2019}
}

Repository licensed under LICENSE.