Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions

Abstract

This letter introduces an abstract learning problem called the "set embedding": The objective is to map sets into probability distributions so as to lose less information. We relate set union and intersection operations with corresponding interpolations of probability distributions. We also demonstrate a preliminary solution with experimental results on toy set embedding examples.

To be presented at Sets & Partitions (NeurIPS 2019 workshop)