5 citations · 19 across the 11 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
stat.ML2021★ 2 cited
The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization
Mufan Bill Li, Mihai Nica, Daniel M. Roy
Theoretical results show that neural networks can be approximated by Gaussian processes in the infinite-width limit. However, for fully connected networks, it has been previously s…
stat.ML2021
Higher Order Generalization Error for First Order Discretization of Langevin Diffusion
Mufan Bill Li, Maxime Gazeau
We propose a novel approach to analyze generalization error for discretizations of Langevin diffusion, such as the stochastic gradient Langevin dynamics (SGLD). For an toleranc…