Despite great progress in simulating multiphysics problems using the numerical
discretization of partial differential equations (PDEs), one still cannot seamlessly incorporate …

Along with the great success of deep neural networks, there is also growing concern about
their black-box nature. The interpretability issue affects people's trust on deep learning …

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant
correlations across multiple training distributions. To achieve this goal, IRM learns a data …

Object detection, one of the most fundamental and challenging problems in computer vision,
seeks to locate object instances from a large number of predefined categories in natural …

Convolutional neural networks (CNNs) are inherently limited to model geometric
transformations due to the fixed geometric structures in its building modules. In this work, we …

Geometric deep learning is an umbrella term for emerging techniques attempting to
generalize (structured) deep neural models to non-Euclidean domains, such as graphs and …

Abstract Convolutional Neural Networks define an exceptionallypowerful class of model, but
are still limited by the lack of abilityto be spatially invariant to the input data in a …

Abstract We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a
natural generalization of convolutional neural networks that reduces sample complexity by …

Modern practice for training classification deepnets involves a terminal phase of training
(TPT), which begins at the epoch where training error first vanishes. During TPT, the training …

Modern convolutional networks are not shift-invariant, as small input shifts or translations
can cause drastic changes in the output. Commonly used downsampling methods, such as …