2 citations · 2 across the 2 of their papers we have counts for
2 papers
math.OC2023
Gradient descent in matrix factorization: Understanding large initialization
Hengchao Chen, Xin Chen, Mohamad Elmasri +1
Gradient Descent (GD) has been proven effective in solving various matrix factorization problems. However, its optimization behavior with large initial values remains less understo…
math.ST2023★ 2 cited
Sketched Ridgeless Linear Regression: The Role of Downsampling
Xin Chen, Yicheng Zeng, Siyue Yang +1
Overparametrization often helps improve the generalization performance. This paper presents a dual view of overparametrization suggesting that downsampling may also help generalize…