Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Sinkhorn doubly stochastic attention rank decay analysis
Michela Lapenna, Rita Fioresi, Bahman Gharesifard
The self-attention mechanism is central to the success of Transformer architectures. However, standard row-stochastic attention has been shown to suffer from significant signal deg…
cs.LG2026
On the Topology of Neural Network Superlevel Sets
Bahman Gharesifard
We show that neural networks with activations satisfying a Riccati-type ordinary differential equation condition, an assumption arising in recent universal approximation results in…