Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method

Convolutions, Polynomials and Flipped Kernels - Eli Bendersky's website

Territory

Jonah Mixon-Webster Where the vision was is when / There are wood panels all over the house shared by many people / and I am a collective member of a white simulation in black face / There is a man…

Understanding convolution on graphs via energies

Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing models act as...

Lattice Convolutional Networks for Learning Ground States of...

Deep learning methods have been shown to be effective in representing ground-state wave functions of quantum many-body systems. Existing methods use convolutional neural networks (CNNs) for square...

Understanding convolution on graphs via energies

Graph Neural Networks (GNNs) typically operate by message-passing, where the state of a node is updated based on the information received from its neighbours. Most message-passing models act as...

Deformation Robust Roto-Scale-Translation Equivariant CNNs

Incorporating group symmetry directly into the learning process has proved to be an effective guideline for model design. By producing features that are guaranteed to transform covariantly to the...

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction