46 citations · 163 across the 24 of their papers we have counts for
6 papers · 1 filter
High Dimensional Binary Classification under Label Shift: Phase Transition and Regularization
Jiahui Cheng, Minshuo Chen, Hao Liu +2
Label Shift has been widely believed to be harmful to the generalization performance of machine learning models. Researchers have proposed many approaches to mitigate the impact of…
Numerical Identification of Nonlocal Potential in Aggregation
Yuchen He, Sung Ha Kang, Wenjing Liao +2
Aggregation equations are broadly used to model population dynamics with nonlocal interactions, characterized by a potential in the equation. This paper considers the inverse probl…
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint
Hao Liu, Minshuo Chen, Siawpeng Er +3
Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization…
An Efficient Operator-Splitting Method for the Eigenvalue Problem of the Monge-Ampère Equation
Hao Liu, Shingyu Leung, Jianliang Qian
We develop an efficient operator-splitting method for the eigenvalue problem of the Monge-Ampère operator in the Aleksandrov sense. The backbone of our method relies on a convergen…
Elastica Models for Color Image Regularization
Hao Liu, Xue-Cheng Tai, Ron Kimmel +1
One classical approach to regularize color is to tream them as two dimensional surfaces embedded in a five dimensional spatial-chromatic space. In this case, a natural regularizati…
Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces
Hao Liu, Haizhao Yang, Minshuo Chen +2
Learning operators between infinitely dimensional spaces is an important learning task arising in wide applications in machine learning, imaging science, mathematical modeling and…