4 citations
2 papers
math.PR2024★ 4 cited
Large deviations of one-hidden-layer neural networks
Christian Hirsch, Daniel Willhalm
We study large deviations in the context of stochastic gradient descent for one-hidden-layer neural networks with quadratic loss. We derive a quenched large deviation principle, wh…
cond-mat.mtrl-sci2024★ 3 cited
A survey of energies from pure metals to multi-principal element alloys
Ruitian Chen, Evelyn Li, Yu Zou
In materials science, a wide range of properties of materials are governed by various types of energies, including thermal, physicochemical, structural, and mechanical energies. In…