Generative Adversarial Networks (GAN) are an effective method for training generative models
of complex data such as natural images. However, they are notoriously hard to train and …

Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets
(eg, calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) …

Humans naturally decompose their environment into entities at the appropriate level of
abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition …

We study unsupervised generative modeling in terms of the optimal transport (OT) problem
between true (but unknown) data distribution $P_X$ and the latent variable model …

Over the past few years, neural networks were proven vulnerable to adversarial images:
targeted but imperceptible image perturbations lead to drastically different predictions. We show …

Kernel mean embeddings have become a popular tool in machine learning. They map
probability measures to functions in a reproducing kernel Hilbert space. The distance between …

We describe a method for removing the effect of confounders to reconstruct a latent quantity
of interest. The method, referred to as “half-sibling regression,” is inspired by recent work in …

… explicitly point out the flaw in the proof of Claim 2 by Simon-Gabriel and Schölkopf (2018). …
The flaw in the proof of Theorem 12 of Simon-Gabriel and Schölkopf (2018) (our Claim 2) …

Over the past four years, neural networks have been proven vulnerable to adversarial images:
targeted but imperceptible image perturbations lead to drastically different predictions. We …

Kernel Stein discrepancies (KSDs) are maximum mean discrepancies (MMDs) that leverage
the score information of distributions, and have grown central to a wide range of applications…