Partial differential equations (PDEs) can describe many relevant phenome...
Studying conditional independence structure among many variables with fe...
We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densit...
Physics-informed Neural Networks (PINNs) have recently emerged as a
prin...
Considering smooth mappings from input vectors to continuous targets, ou...
Identifying meaningful and independent factors of variation in a dataset...
The Neural Tangent Kernel (NTK) is an important milestone in the ongoing...
Symmetry transformations induce invariances and are a crucial building b...
Archetypes are typical population representatives in an extremal sense, ...
Combining the Information Bottleneck model with deep learning by replaci...
Deep models have advanced prediction in many domains, but their lack of
...
The lack of interpretability remains a barrier to the adoption of deep n...
Tensor B-spline methods are a high-performance alternative to solve part...
"Deep Archetypal Analysis" generates latent representations of
high-dime...
Estimating the causal effects of an intervention in the presence of
conf...
Computer vision tasks are difficult because of the large variability in ...
Estimating causal effects in the presence of latent confounding is a
fre...
Deep latent variable models are powerful tools for representation learni...
Many of the benefits we derive from the Internet require trust in the
au...
The lack of interpretability remains a key barrier to the adoption of de...
We propose a new method of discovering causal relationships in temporal ...
This paper considers a Bayesian view for estimating a sub-network in a M...
We present a novel probabilistic clustering model for objects that are
r...
We introduce a copula mixture model to perform dependency-seeking cluste...