Group Symmetry in PAC Learning
Bryn Elesedy
2022 Spotlight
in
Workshop: Geometrical and Topological Representation Learning
in
Workshop: Geometrical and Topological Representation Learning
Abstract
In this paper we show rigorously how learning in the PAC framework with invariant or equivariant hypotheses reduces to learning in a space of orbit representatives. Our results hold for any compact group, including infinite groups such as rotations. In addition, we show how to use these equivalences to derive generalisation bounds for invariant/equivariant models in terms of the geometry of the input and output spaces. To the best of our knowledge, our results are the most general of their kind to date.
Video
Chat is not available.
Successful Page Load