← Search

Anna Sepliarskaia

2 accepted papers

2025

On the VC dimension of deep group convolutional neural networks

NeurIPS 2025poster

Recent works have introduced new equivariant neural networks, motivated by their improved generalization compared to traditional deep neural networks. While experiments support this advantage, the theoretical understanding of their generalization properties remains limited. In this paper, we analyze…

Cited by 0SourceScholar
2022

LieGG: Studying Learned Lie Group Generators

NeurIPS 2022accept

Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them. We depart from the position that when symmetries are not built into a model a priori, it is advantageous for robust networks to learn symmetries directly from the…