Information-Geometric Set Embeddings (IGSE): From Sets to Probability Distributions
Ke Sun, Frank Nielsen · arXiv (Cornell University) · 2019
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.