A significant task in statistics and machine learning currently revolves around generating samples from a target distribution that is only accessible via a dataset.

Bayesian deep learning has always garnered substantial interest in the machine learning community.

While initial breakthroughs on the convergence of gradient optimization in neural networks (Li & Liang, 2018; Du et al., 2019a; Allen-Zhu et al., 2019) required unrealistic conditions on the

In this work, first, we construct and evaluate a straightforward strategy, "impute-then-detect", via combining state-of-the-art imputation methods with unsupervised anomaly detection methods, where the training data are composed of normal samples only.

Algorithmic indistinguishability yields a natural test for assessing whether experts incorporate this kind of "side