We perform scalable approximate inference in continuous-depth Bayesian neural networks.
In this model class, uncertainty about separate weights in each layer gives hidden units that …

The rank of neural networks measures information flowing across layers. It is an instance of
a key structural condition that applies across broad domains of machine learning. In …

The tremendous recent progress in analyzing the training dynamics of overparameterized
neural networks has primarily focused on wide networks and therefore does not sufficiently …

Transformers are extremely successful machine learning models whose mathematical
properties remain poorly understood. Here, we rigorously characterize the behavior of …

The tremendous recent progress in analyzing the training dynamics of over parameterized
neural networks has primarily focused on wide networks and therefore does not sufficiently …

Improving mechanistic understanding and prediction capabilities of long-term organic soil
system dynamics is a high priority for biogeochemists, soil scientists, and climate policy …

We study deep fully-connected neural networks using the mean field formalism, and carry
out a non-perturbative analysis of signal propagation. As a result, we demonstrate that …