A Complete Characterisation of ReLU-Invariant Distributions
by Jan Macdonald, Stephan Wäldchen
Year:
2022
Publication:
25th International Conference on Artificial Intelligence and Statistics
Abstract:
We give a complete characterisation of families of probability distributions that are invariant under the action of ReLU neural network layers (in the same way that the family of Gaussian distributions is invariant to affine linear transformations).
Link:
Read the paperAdditional Information
Brief introduction of the dida co-author(s) and relevance for dida's ML developments.
About the Co-Author
During his studies in mathematics (TU Berlin) Jan focussed on applied topics in optimization, functional analysis, and image processing. His doctoral studies (TU Berlin) explored the interplay between theoretical and empirical research on neural networks. This resulted in his PhD thesis investigating the reliability of deep learning for imaging and computer vision tasks in terms of interpretability, robustness, and accuracy. At dida he works as a Machine Learning Researcher at the interface of scientific research and software development.