Skip to yearly menu bar Skip to main content


Provably Strict Generalisation Benefit for Equivariant Models

Bryn Elesedy · Sheheryar Zaidi


Keywords: [ Architectures ] [ Applications -> Object Detection; Neuroscience and Cognitive Science ] [ Visual Perception ] [ Visual Scene Analysis and Interpretation ]


It is widely believed that engineering a model to be invariant/equivariant improves generalisation. Despite the growing popularity of this approach, a precise characterisation of the generalisation benefit is lacking. By considering the simplest case of linear models, this paper provides the first provably non-zero improvement in generalisation for invariant/equivariant models when the target distribution is invariant/equivariant with respect to a compact group. Moreover, our work reveals an interesting relationship between generalisation, the number of training examples and properties of the group action. Our results rest on an observation of the structure of function spaces under averaging operators which, along with its consequences for feature averaging, may be of independent interest.

Chat is not available.