49 citations · 95 across the 10 of their papers we have counts for
Showing 2024Show all
2 papers · 1 filter
cs.LG2024
Separation Power of Equivariant Neural Networks
Marco Pacini, Xiaowen Dong, Bruno Lepri +1
The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy for its expressivity. Indeed, knowing th…
cs.LG2024
A Characterization Theorem for Equivariant Networks with Point-wise Activations
Marco Pacini, Xiaowen Dong, Bruno Lepri +1
Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains. But for some specific symmetries, representations, and cho…