Symmetries built into a neural network have appeared to be very beneficial for a wide range
of tasks as it saves the data to learn them. We depart from the position that when symmetries …

Recent works on neural contextual bandits have achieved compelling performances due to
their ability to leverage the strong representation power of neural networks (NNs) for reward …

Kernel-based models such as kernel ridge regression and Gaussian processes are
ubiquitous in machine learning applications for regression and optimization. It is well known …

Existing neural active learning algorithms have aimed to optimize the predictive
performance of neural networks (NNs) by selecting data for labelling. However, other than a …

Physics-Informed Neural Networks (PINNs), which incorporate PDEs as soft constraints,
train with a composite loss function that contains multiple training point types: different types …

The success of over-parameterized neural networks trained to near-zero training error has
caused great interest in the phenomenon of benign overfitting, where estimators are …

Modern reinforcement learning (RL) has shown empirical success in various real world
settings with complex models and large state-action spaces. The existing analytical results …

Black box optimisation of an unknown function from expensive and noisy evaluations is a
ubiquitous problem in machine learning, academic research and industrial production. An …

We consider the neural contextual bandit problem. In contrast to the existing work which
primarily focuses on ReLU neural nets, we consider a general set of smooth activation …

Modern reinforcement learning (RL) often faces an enormous state-action space. Existing
analytical results are typically for settings with a small number of state-actions, or simple …