Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Conservation Law Breaking at the Edge of Stability: A Spectral Theory of Non-Convex Neural Network Optimization
Daniel Nobrega Medeiros
Why does gradient descent reliably find good solutions in non-convex neural network optimization, despite the landscape being NP-hard in the worst case? We show that gradient flow…
cs.LG2026
PolyGLU: State-Conditional Activation Routing in Transformer Feed-Forward Networks
Daniel Nobrega Medeiros
Biological neural systems employ diverse neurotransmitters -- glutamate, GABA, dopamine, acetylcholine -- to implement distinct signal-processing modalities within shared neural ci…