10 citations · 23 across the 7 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 3 cited
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective
Jingzhao Zhang, Haochuan Li, Suvrit Sra +1
This work examines the deep disconnect between existing theoretical analyses of gradient-based algorithms and the practice of training deep neural networks. Specifically, we provid…
math.OC2021★ 10 cited
Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization
Haochuan Li, Yi Tian, Jingzhao Zhang +1
We provide a first-order oracle complexity lower bound for finding stationary points of min-max optimization problems where the objective function is smooth, nonconvex in the minim…