3 citations · 10 across the 24 of their papers we have counts for
24 papers
Risk Equivalence between RKHS Regression and Sequence Models for Lipschitz Spectral Algorithms
Yicheng Li, Yuqian Cheng, Zhuo Chen +1
Kernel spectral algorithms are often summarized by convergence rates, which hide how their risk depends jointly on regularization, noise, the population spectrum, target coefficien…
Exact Generalization Error Curves of Kernel Ridge Regression for Functional Moment Estimation
Yinan Ding, Yicheng Li
Kernel ridge regression is a standard method for functional data analysis, but its exact behavior is less understood. We study tensor-product kernel ridge regression for estimating…
AMO: Operator-level Adaptive Muon Orthogonalization
Xinlin Zhuang, Panyi Ouyang, Yichen Li +7
Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iteration as its core operation. Standar…
Large Dimensional Kernel Ridge Regression: Extending to Product Kernels
Yang Zhou, Yicheng Li, Yuqian Cheng +1
Recent studies have reported and in large dimensional kernel ridge regression (KRR). However, these findings are…
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
T. Tony Cai, Yicheng Li
Federated differentially private protocols can communicate over many adaptive rounds and reuse each client's local samples. Existing lower bound arguments for federated DP are ofte…
PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers
Quanhao Ren, Yicheng Li, Nan Song
Motion forecasting is a core task in autonomous driving systems, aiming to accurately predict the future trajectories of surrounding agents to ensure driving safety. Existing metho…
Supporting Evidence for the Adaptive Feature Program across Diverse Models
Yicheng Li, Qian Lin
Theoretically exploring the advantages of neural networks might be one of the most challenging problems in the AI era. An adaptive feature program has recently been proposed to ana…
Alignment-Sensitive Minimax Rates for Spectral Algorithms with Learned Kernels
Dongming Huang, Zhifan Li, Yicheng Li +1
We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensitive complexity measure that dep…
Neural Tangent Kernel of Neural Networks with Loss Informed by Differential Operators
Weiye Gan, Yicheng Li, Qian Lin +1
Spectral bias is a significant phenomenon in neural network training and can be explained by neural tangent kernel (NTK) theory. In this work, we develop the NTK theory for deep ne…
On the Saturation Effects of Spectral Algorithms in Large Dimensions
Weihao Lu, Haobo Zhang, Yicheng Li +1
The saturation effects, which originally refer to the fact that kernel ridge regression (KRR) fails to achieve the information-theoretical lower bound when the regression function…
Diagonal Over-parameterization in Reproducing Kernel Hilbert Spaces as an Adaptive Feature Model: Generalization and Adaptivity
Yicheng Li, Qian Lin
This paper introduces a diagonal adaptive kernel model that dynamically learns kernel eigenvalues and output coefficients simultaneously during training. Unlike fixed-kernel method…
Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories
Yicheng Li, Haobo Zhang, Jianfa Lai +2
A primary advantage of neural networks lies in their feature learning characteristics, which is challenging to theoretically analyze due to the complexity of their training dynamic…
Improving Adaptivity via Over-Parameterization in Sequence Models
Yicheng Li, Qian Lin
It is well known that eigenfunctions of a kernel play a crucial role in kernel regression. Through several examples, we demonstrate that even with the same set of eigenfunctions, t…
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
Guhan Chen, Yicheng Li, Qian Lin
This paper aims to discuss the impact of random initialization of neural networks in the neural tangent kernel (NTK) theory, which is ignored by most recent works in the NTK theory…
Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions
Haobo Zhang, Yicheng Li, Weihao Lu +1
Motivated by the studies of neural networks (e.g.,the neural tangent kernel theory), we perform a study on the large-dimensional behavior of kernel ridge regression (KRR) where the…
Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay
Yicheng Li, Weiye Gan, Zuoqiang Shi +1
The generalization error curve of certain kernel regression method aims at determining the exact order of generalization error with various source condition, noise level and choice…
On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
Yicheng Li, Haobo Zhang, Qian Lin
The widely observed 'benign overfitting phenomenon' in the neural network literature raises the challenge to the 'bias-variance trade-off' doctrine in the statistical learning theo…
Optimal Rate of Kernel Regression in Large Dimensions
Weihao Lu, Haobo Zhang, Yicheng Li +2
We perform a study on kernel regression for large-dimensional data (where the sample size is polynomially depending on the dimension of the samples, i.e., for…
On the Optimality of Misspecified Kernel Ridge Regression
Haobo Zhang, Yicheng Li, Weihao Lu +1
In the misspecified kernel ridge regression problem, researchers usually assume the underground true function , a less-smooth interpolation space of…
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
Yicheng Li, Zixiong Yu, Guhan Chen +1
In this paper, we provide a strategy to determine the eigenvalue decay rate (EDR) of a large class of kernel functions defined on a general domain rather than . This…
Kernel interpolation generalizes poorly
Yicheng Li, Haobo Zhang, Qian Lin
One of the most interesting problems in the recent renaissance of the studies in kernel regression might be whether the kernel interpolation can generalize well, since it may help…
On the Optimality of Misspecified Spectral Algorithms
Haobo Zhang, Yicheng Li, Qian Lin
In the misspecified spectral algorithms problem, researchers usually assume the underground true function , a less-smooth interpolation space of a re…
A non-local gradient based approach of infinity Laplacian with -convergence
Weiye Gan, Xintong Liu, Yicheng Li +1
We propose an infinity Laplacian method to address the problem of interpolation on an unstructured point cloud. In doing so, we find the labeling function with the smallest infinit…
Moment bounds for large autocovariance matrices under dependence
Fang Han, Yicheng Li
The goal of this paper is to obtain expectation bounds for the deviation of large sample autocovariance matrices from their means under weak data dependence. While the accuracy of…