A Generative Model of Symmetry Transformations

arXiv:2403.01946v1 Announce Type: new
Abstract: Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made in learning those symmetries directly from the dataset, most of this work has focused on the discriminative setting. In this paper, we construct a generative model that explicitly aims to capture symmetries in the data, resulting in a model that learns which symmetries are present …

abstract arxiv capabilities cs.lg data dataset generative knowledge prior symmetry type work