Yicheng Li

According to our database, Yicheng Li authored at least 19 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Several Supporting Evidences for the Adaptive Feature Program.

Yicheng Li, Qian Lin

CoRR, November, 2025

Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels.

Dongming Huang, Zhifan Li, Yicheng Li, Qian Lin

CoRR, September, 2025

Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators.

Weiye Gan, Yicheng Li, Qian Lin, Zuoqiang Shi

CoRR, March, 2025

Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity.

Yicheng Li, Qian Lin

CoRR, January, 2025

Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions.

Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

J. Mach. Learn. Res., 2025

2024

On the Optimality of Misspecified Spectral Algorithms.

Haobo Zhang, Yicheng Li, Qian Lin

J. Mach. Learn. Res., 2024

On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains.

Yicheng Li, Zixiong Yu, Guhan Chen, Qian Lin

J. Mach. Learn. Res., 2024

Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories.

Haobo Zhang, Jianfa Lai, Yicheng Li, Qian Lin, Jun S. Liu

CoRR, 2024

Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay.

Yicheng Li, Weiye Gan, Zuoqiang Shi, Qian Lin

CoRR, 2024

Improving Adaptivity via Over-Parameterization in Sequence Models.

Yicheng Li, Qian Lin

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory.

Guhan Chen, Yicheng Li, Qian Lin

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

On the Saturation Effects of Spectral Algorithms in Large Dimensions.

Weihao Lu, Haobo Zhang, Yicheng Li, Qian Lin

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Optimal Rate of Kernel Regression in Large Dimensions.

Weihao Lu, Haobo Zhang, Yicheng Li, Manyun Xu, Qian Lin

CoRR, 2023

Statistical Optimality of Deep Wide Neural Networks.

Yicheng Li, Zixiong Yu, Guhan Chen, Qian Lin

CoRR, 2023

Kernel interpolation generalizes poorly.

Yicheng Li, Haobo Zhang, Qian Lin

CoRR, 2023

On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay.

Yicheng Li, Haobo Zhang, Qian Lin

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On the Optimality of Misspecified Kernel Ridge Regression.

Haobo Zhang, Yicheng Li, Weihao Lu, Qian Lin

Proceedings of the International Conference on Machine Learning, 2023

On the Saturation Effect of Kernel Ridge Regression.

Yicheng Li, Haobo Zhang, Qian Lin

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

A non-local gradient based approach of infinity Laplacian with Γ-convergence.

Weiye Gan, Xintong Liu, Yicheng Li, Zuoqiang Shi

CoRR, 2022