Repository for the paper Lipschitz Regularity of deep neural networks: analysis and efficient estimation
Basic Python dependencies needed: PyTorch >= 0.3
lipschitz_approximations.py
: many estimatorslipschitz_utils.py
: toolbox for the different estimatorsseqlip.py
: SeqLip and GreedySeqLiptraining.py
: general scheme for train/testutils.py
: utility functions