1 citations · 1 across the 4 of their papers we have counts for
4 papers
Unbounded Density Ratio Estimation and Its Application to Covariate Shift Adaptation
Ren-Rui Liu, Jun Fan, Lei Shi +1
This paper focuses on the problem of unbounded density ratio estimation -- an understudied yet critical challenge in statistical learning -- and its application to covariate shift…
Variance-Aware Adaptive Weighting for Diffusion Model Training
Nanlong Sun, Lei Shi
Diffusion models have recently achieved remarkable success in generative modeling, yet their training dynamics across different noise levels remain highly imbalanced, which can lea…
Spectral Algorithms under Covariate Shift
Jun Fan, Zheng-Chu Guo, Lei Shi
Spectral algorithms leverage spectral regularization techniques to analyze and process data, providing a flexible framework for addressing supervised learning problems. To deepen o…
Generalization Analysis of Online Stochastic Gradient Descent for Overparameterized Two-Layer Neural Networks
Dinghao Cao, Zheng-Chu Guo, Lei Shi
We investigate the generalization performance of online stochastic gradient descent (SGD) for overparameterized two-layer neural networks under the Neural Tangent Kernel (NTK) regi…