3 papers
stat.ML2026
Minimax-Optimal Generalization Bounds for Smooth Deep Neural Networks Trained by (Stochastic) Gradient Descent
Junyu Zhou, Puyu Wang, Yunwen Lei +3
Characterizing the optimization dynamics and statistical performance of over-parameterized deep neural networks (DNNs) remains a central challenge in understanding the remarkable s…
stat.ML2026
Optimal Rates for Generalization of Gradient Descent Methods with Deep Neural Networks
Junyu Zhou, Puyu Wang, Yunwen Lei +2
Recent progress has been made in understanding the statistical generalization performance of gradient descent methods for overparameterized neural networks within the neural tangen…
stat.ML2026
Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents
Xiaotong Liu, Yunwen Lei, Xiangyu Chang +1
This paper proposes a novel parameter selection strategy for kernel-based gradient descent (KGD) algorithms, integrating bias-variance analysis with the splitting method. We introd…