Neural ODE Processes approach the problem of meta-learning for dynamics using a latent
variable model, which permits a flexible aggregation of contextual information. This flexibility …

Modeling the dynamics of real-world physical systems is critical for spatiotemporal prediction
tasks, but challenging when data is limited. The scarcity of real-world data and the difficulty …

We propose a new model class aimed at predicting dynamical trajectories from high-
dimensional empirical data. This is done by combining variational autoencoders and (spatio …

Neural Processes (NPs; Garnelo et al., 2018a, b) are a rich class of models for meta-
learning that map data sets directly to predictive stochastic processes. We provide a rigorous …

We propose HyperDynamics, a dynamics meta-learning framework that conditions on an
agent's interactions with the environment and optionally its visual observations, and …

Learning representations of stochastic processes is an emerging problem in machine
learning with applications from meta-learning to physical object models to time series …

Machine learning methods can be a valuable aid in the scientific process, but they need to
face challenging settings where data come from inhomogeneous experimental conditions …

Meta-learning aims to develop algorithms that can learn from other learning algorithms to
adapt to new and changing environments. This requires a model of how other learning …

Modern applications increasingly require unsupervised learning of latent dynamics from
high-dimensional time-series. This presents a significant challenge of identifiability: many …

Abstract Model-agnostic meta-learners aim to acquire meta-learned parameters from similar
tasks to adapt to novel tasks from the same distribution with few gradient updates. With the …