Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
Publication information:
M. Farrell*, B. Bordelon*, S. Trivedi, and C. Pehlevan,
“Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?”, in NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations (Oral), 2022.