This code repo contains the implementation for the Meta-SGLD algorithm presented in the NeurIPS 2021 paper Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis by Chen, Shui, and Marchand.
To run the code, make sure that the requirements are installed.
pip install -r requirements.txt
The code was written to run in Python 3.6 or in a more recent version.
python src/main/toy_exp/toy.py
python src/main/omniglot_train.py
The program will download omniglot dataset automatically.
The code is modified and implemented based on https://github.com/ron-amit/meta-learning-adjusting-priors2 and https://github.com/dragen1860/MAML-Pytorch.