225 citations · 303 across the 17 of their papers we have counts for
5 papers · 1 filter
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Xiangyu Chang, Yingcong Li, Samet Oymak +1
Deep networks are typically trained with many more parameters than the size of the training dataset. Recent empirical evidence indicates that the practice of overparameterization n…
Kernel Interpolation of High Dimensional Scattered Data
Shao-Bo Lin, Xiangyu Chang, Xingping Sun
Data sites selected from modeling high-dimensional problems often appear scattered in non-paternalistic ways. Except for sporadic clustering at some spots, they become relatively f…
Randomized spectral co-clustering for large-scale directed networks
Xiao Guo, Yixuan Qiu, Hai Zhang +1
Directed networks are broadly used to represent asymmetric relationships among units. Co-clustering aims to cluster the senders and receivers of directed networks simultaneously. I…
Randomized Spectral Clustering in Large-Scale Stochastic Block Models
Hai Zhang, Xiao Guo, Xiangyu Chang
Spectral clustering has been one of the widely used methods for community detection in networks. However, large-scale networks bring computational challenges to the eigenvalue deco…
Adaptive Stopping Rule for Kernel-based Gradient Descent Algorithms
Xiangyu Chang, Shao-Bo Lin
In this paper, we propose an adaptive stopping rule for kernel-based gradient descent (KGD) algorithms. We introduce the empirical effective dimension to quantify the increments of…