Instead, we impose a condition on the residual variances that is closely related to previous work on linear models with equal variances.

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.