Deep learning has had tremendous success at learning low-dimensional representations of
high-dimensional data. This success would be impossible if there was no hidden low …

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 …

We present the results of the" Fast Calorimeter Simulation Challenge 2022"-the
CaloChallenge. We study state-of-the-art generative models on four calorimeter shower …

Why can pre-trained language models (PLMs) learn universal representations and
effectively adapt to broad NLP tasks differing a lot superficially? In this work, we empirically …

How many degrees of freedom are there in a dataset consisting of $ M $ samples embedded
in $\mathbb {R}^ D $? This number, formally known as\textsl {intrinsic dimensionality}, can …

Abstract Generative Models (GMs) have attracted considerable attention due to their
tremendous success in various domains, such as computer vision where they are capable to …

We present a nonparametric method for outlier detection that takes full account of local
variations in intrinsic dimensionality within the dataset. Using the theory of Local Intrinsic …

Properties of data distributions can be assessed at both global and local scales. At a highly
localized scale, a fundamental measure is the local intrinsic dimensionality (LID), which …

Likelihood-based deep generative models have recently been shown to exhibit pathological
behaviour under the manifold hypothesis as a consequence of using high-dimensional …

Introduction In brain-computer interfaces (BCI) research, recording data is time-consuming
and expensive, which limits access to big datasets. This may influence the BCI system …