78 citations · 121 across the 12 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Hidden symmetries of ReLU networks
J. Elisenda Grigsby, Kathryn Lindsey, David Rolnick
The parameter space for any fixed architecture of feedforward ReLU neural networks serves as a proxy during training for the associated class of functions - but how faithful is thi…
cs.LG2023★ 1 cited
PGrad: Learning Principal Gradients For Domain Generalization
Zhe Wang, Jake Grigsby, Yanjun Qi
Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG t…