The bound is based on a novel parametric form of the Chebyshev-Cantelli inequality (a.k.a.

Machine learning (ML) models often exhibit unexpected failures once deployed in the "wild".

Currently, the data augmentation parameters are chosen by human effort and costly cross-validation, which makes it cumbersome to apply to new datasets. We develop a convenient gradient-based method for selecting the data augmentation without validation data during training of a deep neural network.

Because the true underlying structure of the data is rarely accessible, this "representation learning" must be

Several queries and scores have been proposed to explain individual predictions made by ML models. Examples include queries based on "anchors", which are parts of an instance that are sufficient to justify its classification, and "feature-perturbation" scores such as SHAP .

For the GP, the bias-variance trade-off is made by optimization of the two hyperparameters: the length scale and noise-term.

Thus, we restrict our search for a constrained clustering approach to the class of deep generative models. Although these models have been successfully used in the unsupervised setting (Jiang et al., 2017; Dilokthanakul et al., 2016), their application to constrained clustering has been under-explored.