When developing deep learning models, we usually decide what task we want to solve then search for a model that generalizes well on the task. An intriguing question would be: what if, instead of fixing the task and searching in the model space, we fix the model and search in the task space?

However, this label set is not necessarily representative of what occurs in the data: there may exist labels in the knowledge base that do not occur in the corpus because the sense is rare in modern English; conversely, there may also exist true labels that do not exist in our knowledge base. For example, consider the word "bass."

Our method extends recent developments in simulation-based inference (SBI) based on normalizing flows to Bayesian hierarchical models.

Graph neural networks (GNNs) (Zhou et al., 2018; Zhang et al., 2020) have been widely used on graph-structured data to obtain a meaningful representation of nodes in the graph.

We develop the first polynomial-time algorithms that return a near-optimal solution with high probability.

We propose a new algorithm called GenTD for off-policy GVFs evaluation and show that GenTD learns multiple interrelated multidimensional GVFs as efficiently as a single canonical scalar value function.