Abstract for the talk on 13.04.2023 (17:00 h)
Math Machine Learning seminar MPI MIS + UCLAWei Zhu (University of Massachusetts Amherst)
Implicit Bias of Linear Equivariant Steerable Networks
See the video of this talk.
See the slides of this talk.
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.