Recent years have seen many insights on deep learning optimisation being...
Recent progress has been made in understanding optimisation dynamics in
...
In many contexts, simpler models are preferable to more complex models a...
Gradient-based methods for two-player games produce rich dynamics that c...
Most of the recent deep reinforcement learning advances take an RL-centr...
How sensitive should machine learning models be to input changes? We tac...
This paper is a broad and accessible survey of the methods we have at ou...
Generative Adversarial Networks (GANs) enjoy great success at image
gene...
Compressed sensing (CS) provides an elegant framework for recovering spa...
We propose a method of moments (MoM) algorithm for training large-scale
...
The difficulties in matching the latent posterior to the prior, balancin...
Generative adversarial networks (GANs) are a family of generative models...
Auto-encoding generative adversarial networks (GANs) combine the standar...
Transliteration is a key component of machine translation systems and
so...