The rapid uptake of mobile devices and the rising popularity of mobile applications and
services pose unprecedented demands on mobile and wireless networking infrastructure …

Traditional recommender systems typically use user-item rating histories as their main data
source. However, deep generative models now have the capability to model and sample …

In-context learning is the ability of a model to condition on a prompt sequence consisting of
in-context examples (input-output pairs corresponding to some task) along with a new query …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Deep neural networks provide unprecedented performance gains in many real-world
problems in signal and image processing. Despite these gains, the future development and …

It is common practice in deep learning to represent a measurement of the world on a
discrete grid, eg a 2D grid of pixels. However, the underlying signal represented by these …

Gradient-based meta-learning techniques are both widely applicable and proficient at
solving challenging few-shot learning and fast adaptation problems. However, they have …

Learning the distribution of a continuous or categorical response variable y given its
covariates x is a fundamental problem in statistics and machine learning. Deep neural …

Neural Processes (NPs) are a popular class of approaches for meta-learning. Similar to
Gaussian Processes (GPs), NPs define distributions over functions and can estimate …

Neural Processes (NPs)(Garnelo et al 2018a; b) approach regression by learning to map a
context set of observed input-output pairs to a distribution over regression functions. Each …