While prior domain generalization (DG) benchmarks consider train-test da...
Learning latent causal models from data has many important applications ...
Denoising Diffusion models have shown remarkable capabilities in generat...
A distribution shift can have fundamental consequences such as signaling...
Unsupervised distribution alignment estimates a transformation that maps...
While normalizing flows for continuous data have been extensively resear...
While previous distribution shift detection approaches can identify if a...
The task of mapping two or more distributions to a shared representation...
Shapley values have become one of the most popular feature attribution
e...
Adversarial examples (AEs) are images that can mislead deep neural netwo...
In safety-critical applications of machine learning, it is often necessa...
The Poisson distribution has been widely studied and used for modeling
u...
We present a novel k-way high-dimensional graphical model called the
Gen...
We develop Square Root Graphical Models (SQR), a novel class of parametr...