no code implementations • NeurIPS 2021 • Daniella Horan, Eitan Richardson, Yair Weiss
In this paper, we show that the assumption of local isometry together with non-Gaussianity of the factors, is sufficient to provably recover disentangled representations from data.
2 code implementations • 24 Jul 2020 • Eitan Richardson, Yair Weiss
Unsupervised image-to-image translation is an inherently ill-posed problem.
no code implementations • 20 Feb 2020 • Eitan Richardson, Yair Weiss
Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural architectures and training methods or an inevitable "feature" of high dimensional geometry.
3 code implementations • NeurIPS 2018 • Eitan Richardson, Yair Weiss
While GMMs have previously been shown to be successful in modeling small patches of images, we show how to train them on full sized images despite the high dimensionality.