Birkhoff polytope
PulseAugur coverage of Birkhoff polytope — every cluster mentioning Birkhoff polytope across labs, papers, and developer communities, ranked by signal.
-
New GNN architecture mHC-GNN tackles over-smoothing and expressiveness limits
Researchers have developed a new Graph Neural Network (GNN) architecture called mHC-GNN, which addresses the common issues of over-smoothing and limited expressiveness in deep GNNs. By adapting manifold-constrained hype…
-
New method matches correlated VAR time series databases
Researchers have developed a new method for matching correlated Vector Autoregressive (VAR) time series databases. The approach introduces a probabilistic framework to recover hidden permutations between two time series…
-
KromHC improves neural network training with Kronecker products
Researchers have introduced KromHC, a novel method for improving neural network training stability and scalability. KromHC addresses limitations in existing Hyper-Connections (HC) by using Kronecker products of smaller …
-
New TBP parameterizations enhance hyper-connection expressivity and stability
Researchers have introduced Transportation Birkhoff Polytope (TBP) parameterizations as a novel method for constructing exactly doubly stochastic mixing matrices in hyper-connections. This approach offers full expressiv…