The effectiveness of machine learning algorithms arises from being able to extract useful
features from large amounts of data. As model and dataset sizes increase, dataset …

One of the most fundamental aspects of any machine learning algorithm is the training data
used by the algorithm. We introduce the novel concept of $\epsilon $-approximation of …

We perform a careful, thorough, and large scale empirical study of the correspondence
between wide neural networks and kernel methods. By doing so, we resolve a variety of …

Many problems in machine learning involve bilevel optimization (BLO), including
hyperparameter optimization, meta-learning, and dataset distillation. Bilevel problems …

We explore the link between deep ensembles and Gaussian processes (GPs) through the
lens of the Neural Tangent Kernel (NTK): a recent development in understanding the …

Parametrized quantum circuits can be used as quantum neural networks and have the
potential to outperform their classical counterparts when trained for addressing learning …

Variational quantum circuits are used in quantum machine learning and variational quantum
simulation tasks. Designing good variational circuits or predicting how well they perform for …

As its width tends to infinity, a deep neural network's behavior under gradient descent can
become simplified and predictable (eg given by the Neural Tangent Kernel (NTK)), if it is …

Recent works have shown that gradient descent can find a global minimum for over-
parameterized neural networks where the widths of all the hidden layers scale polynomially …

The push to train ever larger neural networks has motivated the study of initialization and
training at large network width. A key challenge is to scale training so that a network's …