Harmonic Machine Learning Models are Robust

arXiv:2404.18825v1 Announce Type: new
Abstract: We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels. It is based on functional deviation from the harmonic mean value property, indicating instability and lack of explainability. We show implementation examples in low-dimensional trees and feedforward NNs, where the method reliably identifies overfitting, as well as in more complex high-dimensional models such as ResNet-50 and …

abstract arxiv box cs.ai cs.cv cs.lg deviation explainability functional ground-truth inference labels machine machine learning machine learning models mean monitoring property real-time robust robustness show test training truth type value