Meta-learning using privileged information for dynamics
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 …
variable model, which permits a flexible aggregation of contextual information. This flexibility …
Physics-aware spatiotemporal modules with auxiliary tasks for meta-learning
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 …
tasks, but challenging when data is limited. The scarcity of real-world data and the difficulty …
Invariance-based learning of latent dynamics
K Lagemann, C Lagemann… - The Twelfth International …, 2023 - openreview.net
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 …
dimensional empirical data. This is done by combining variational autoencoders and (spatio …
The Gaussian neural process
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 …
learning that map data sets directly to predictive stochastic processes. We provide a rigorous …
Hyperdynamics: Meta-learning object and agent dynamics with hypernetworks
We propose HyperDynamics, a dynamics meta-learning framework that conditions on an
agent's interactions with the environment and optionally its visual observations, and …
agent's interactions with the environment and optionally its visual observations, and …
On contrastive representations of stochastic processes
Learning representations of stochastic processes is an emerging problem in machine
learning with applications from meta-learning to physical object models to time series …
learning with applications from meta-learning to physical object models to time series …
Interpretable Meta-Learning of Physical Systems
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 …
face challenging settings where data come from inhomogeneous experimental conditions …
Meta Neural Coordination
Y Sun - arXiv preprint arXiv:2305.12109, 2023 - arxiv.org
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 …
adapt to new and changing environments. This requires a model of how other learning …
Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework
Modern applications increasingly require unsupervised learning of latent dynamics from
high-dimensional time-series. This presents a significant challenge of identifiability: many …
high-dimensional time-series. This presents a significant challenge of identifiability: many …
Multimodal model-agnostic meta-learning via task-aware modulation
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 …
tasks to adapt to novel tasks from the same distribution with few gradient updates. With the …