Implicit Bias of Linear Equivariant Steerable Networks
- Wei Zhu (University of Massachusetts Amherst)
I will present, in this talk, the implicit bias of gradient flow on linear equivariant steerable networks in group-invariant binary classification. Our findings reveal that the parameterized predictor converges in direction to the unique group-invariant classifier with a maximum margin defined by the input group action. Under a unitary assumption on the input representation, we establish the equivalence between steerable networks and data augmentation. Furthermore, we demonstrate the improved margin and generalization bound of steerable networks over their non-invariant counterparts. This talk is based on a joint work with Ziyu Chen at UMass Amherst.