Autonomous driving is of great interest to industry and academia alike. The use of machine
learning approaches for autonomous driving has long been studied, but mostly in the …

We show that a variety of modern deep learning tasks exhibit a'double-
descent'phenomenon where, as we increase model size, performance first gets worse and …

Breakthroughs in machine learning are rapidly changing science and society, yet our
fundamental understanding of this technology has lagged far behind. Indeed, one of the …

Message Passing Neural Networks (MPNNs) are a common type of Graph Neural Network
(GNN), in which each node's representation is computed recursively by aggregating …

Driving requires reacting to a wide variety of complex environment conditions and agent
behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation …

Deep learning algorithms are responsible for a technological revolution in a variety of tasks
including image recognition or Go playing. Yet, why they work is not understood. Ultimately …

The “double descent” risk curve was proposed to qualitatively describe the out-of-sample
prediction accuracy of variably parameterized machine learning models. This article …

We empirically show that the test error of deep networks can be estimated by simply training
the same architecture on the same training set but with a different run of Stochastic Gradient …

Knowledge distillation is an effective approach to leverage a well-trained network or an
ensemble of them, named as the teacher, to guide the training of a student network. The …

We study generalised linear regression and classification for a synthetically generated
dataset encompassing different problems of interest, such as learning with random features …