most citedProvable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks

4 citations · 7 across the 2 of their papers we have counts for

collaborators
Showing math.OCShow all

1 paper · 1 filter

math.OC2021★ 3 cited

Explicit Superlinear Convergence Rates of The SR1 Algorithm

Haishan Ye, Dachao Lin, Zhihua Zhang +1

We study the convergence rate of the famous Symmetric Rank-1 (SR1) algorithm which has wide applications in different scenarios. Although it has been extensively investigated, SR1…