3 citations · 7 across the 16 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021
A New Measure of Model Redundancy for Compressed Convolutional Neural Networks
Feiqing Huang, Yuefeng Si, Yao Zheng +1
While recently many designs have been proposed to improve the model efficiency of convolutional neural networks (CNNs) on a fixed resource budget, theoretical understanding of thes…
stat.ME2021
Quantile index regression
Yingying Zhang, Yuefeng Si, Guodong Li +1
Estimating the structures at high or low quantiles has become an important subject and attracted increasing attention across numerous fields. However, due to data sparsity at tails…
stat.ME2021★ 3 cited
An Asymptotic Analysis of Minibatch-Based Momentum Methods for Linear Regression Models
Yuan Gao, Xuening Zhu, Haobo Qi +3
Momentum methods have been shown to accelerate the convergence of the standard gradient descent algorithm in practice and theory. In particular, the minibatch-based gradient descen…