Selected Publications

1. TPM

   Exploiting Inferential Structure in Neural Processes

   Tailor, Dharmesh, Khan, Mohammad Emtiyaz, and Nalisnick, Eric

   In 5th Workshop on Tractable Probabilistic Modeling at UAI 2022 Aug 2022

   Abs PDF

   Neural processes (NPs) can be extremely fast at test time, but their training requires a wide range of context sets to generalize well. We propose to address this issue by incorporating the structure of graphical models into NPs. This leads to aggregation strategies in which context points are appropriately weighted, generalizing a recent proposal by Volpp et al., [2020]. The weighting further reveals an interpretation of each point, which we refer to as the neural sufficient statistics. It is expected that by exploiting information in structured priors, the data inefficiency of NPs can be alleviated.