In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalizationability on the test set.

This paper considers label-level noise in image sensory anomaly detection for thefirsttime.

Graph neural networks (GNNs) have received extensive attention from researchers due to their excellent performance on various graph learning tasks such as social analysis [24, 17, 29], drug discovery [12, 25], traffic forecasting [18, 3, 6], recommendation system [38, 32] and computer vision[39,4].

Our results extend recent developments innonlinear ICA, and in fact, they lead to an important generalization of ICA models. In particular, we show that our model can be used for the estimation of the components in theframeworkofIndependentlyModulatedComponentAnalysis(IMCA),anew generalization of nonlinear ICA that relaxes the independence assumption.

Step decay step-size schedules (constant and then cut) are widely used in practice because of their excellent convergence and generalization qualities, but their theoretical properties are not yet well understood. Weprovide convergence results for step decay in the non-convexregime, ensuring that the gradient norm vanishes at an O(lnT/ T)rate.