9
Modularity and compositionality are promising inductive biases for addressing longstanding problems in machine learning such as better …
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to …
We introduce Breadth-First Pipeline Parallelism, a novel training schedule which optimizes the combination of pipeline and data …
Building causal graphs can be a laborious process. To ensure all relevant causal pathways have been captured, researchers often have to …
Unsupervised skill learning aims to learn a rich repertoire of behaviors without external supervision, providing artificial agents with …
Neural networks are known to fail with high confidence, especially for data that somehow differs from the training distribution. Such …
Handling out-of-distribution (OOD) and adversarial inputs has become a major stake in the real-world deployment of machine learning …
We extend score-based generative diffusion processes (GDPs) to sparse graphs and other inherently discrete data, with a focus on …
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset of …
Recently continuous relaxations have been proposed in order to learn directed acyclic graphs (DAGs) by backpropagation, instead of …