As deep generative models have progressed, recent work has shown them to be capable of
memorizing and reproducing training datapoints when deployed. These findings call into …

Out-of-distribution (OOD) detection aims to detect test samples outside the training category
space, which is an essential component in building reliable machine learning systems …

Generative diffusion processes are state-of-the-art machine learning models deeply
connected with fundamental concepts in statistical physics. Depending on the dataset size …

Likelihood-based deep generative models (DGMs) have gained significant attention for their
ability to approximate the distributions of high-dimensional data. However, these models …

Unsupervised out-of-distribution (U-OOD) detection is to identify OOD data samples with a
detector trained solely on unlabeled in-distribution (ID) data. The likelihood function …

Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent
years thanks to the progress in deep neural networks and generative modeling. In …

In this study, we propose a novel approach to anomaly detection in the tabular domain using
normalizing flows, leveraging a simple likelihood test to achieve state-of-the-art performance …