Solutions to this inverse and ill-posed problem typically involve a search for models that best explain observed image data.

From a computational standpoint, we show that under certain assumptions, adversarial training can detect the presence of backdoors in a training set.

Our theoretical results and experiments on static real-world datasets with simulated dynamics show that our framework can be used to facilitate social science studies.

We propose contrastive coding to learn shared, dense image representations, referred to as CoMIRs (Contrastive Multimodal Image Representations).

Despite their successes, modern neural networks (NNs) still suffer from several shortcomings that limit their applicability in some settings.

Algorithmic stability is a key characteristic of an algorithm regarding its sensitivity to perturbations of input samples. In this paper, we propose an innovative unsupervised feature selection algorithm attaining this stability with provable guarantees.