Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Large Spikes in Stochastic Gradient Descent: A Large-Deviations View
Benjamin Gess, Daniel Heydecker
Large loss spikes in stochastic gradient descent are studied through a rigorous large-deviations analysis for a shallow, fully connected network in the NTK scaling. In contrast to…
math.PR2026
The Porous Medium Equation: Multiscale Integrability in Large Deviations
Benjamin Gess, Daniel Heydecker
We consider a zero-range process with superlinear local jump rate, which in a hydrodynamic-small particle rescaling converges to the porous medium equation $\partial_t u…