Learning Generative Models with Invariance to Symmetries

James Urquhart Allingham, Javier Antoran, Shreyas Padhy, Eric Nalisnick, José Miguel Hernández-Lobato

Keywords: deep generative models, learned invariance, symmetry

TL;DR: We learn deep generative models with invariance to symmetries.

Abstract: While imbuing a model with invariance under symmetry transformations can improve data efficiency and predictive performance, most methods require specialised architectures and, thus, prior knowledge of the symmetries. Unfortunately, we don’t always know what symmetries are present in the data. Recent work has solved this problem by jointly learning the invariance (or the degree of invariance) with the model from the data alone. But, this work has focused on discriminative models. We describe a method for learning invariant generative models. We demonstrate that our method can learn a generative model of handwritten digits that is invariant to rotation.