activity
20192023
most citedGram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems

29 citations · 63 across the 4 of their papers we have counts for

collaborators
Showing 2019Show all

3 papers · 1 filter

stat.ML2019★ 27 cited

Distillation Early Stopping? Harvesting Dark Knowledge Utilizing Anisotropic Information Retrieval For Overparameterized Neural Network

Bin Dong, Jikai Hou, Yiping Lu +1

Distillation is a method to transfer knowledge from one model to another and often achieves higher accuracy with the same capacity. In this paper, we aim to provide a theoretical u…

math.PR2019

Empirical Process of Multivariate Gaussian under General Dependence

Jikai Hou

This paper explores certain kinds of empirical process with respect to the components of multivariate Gaussian. We put forward some finite sample bounds which hold for multivariate…

cs.LG2019★ 29 cited

Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems

Tianle Cai, Ruiqi Gao, Jikai Hou +5

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks. Second-order methods, despite their better con…