6 papers
Weighted Laplacian Flow: A Deterministic Particle Flow with Provable Convergence
Weiye Gan, Tangjun Wang, Zuoqiang Shi
Sampling from a target probability density is a fundamental task in statistics, machine learning, and scientific computing. We introduce weighted Laplacian flow, a deterministic pa…
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…
An Efficient Conditional Score-based Filter for High Dimensional Nonlinear Filtering Problems
Zhijun Zeng, Weiye Gan, Junqing Chen +1
In many engineering and applied science domains, high-dimensional nonlinear filtering is still a challenging problem. Recent advances in score-based diffusion models offer a promis…
Kernel Variational Inference Flow for Nonlinear Filtering Problem
Weiye Gan, Zhijun Zeng, Junqing Chen +1
We present a novel particle flow for sampling called kernel variational inference flow (KVIF). KVIF do not require the explicit formula of the target distribution which is usually…
A Nonlocal Biharmonic Model with -Convergence to Local Model and an Efficient Numerical Method
Weiye Gan, Tangjun Wang, Qiang Du +1
Nonlocal models and their associated theories have been extensively investigated in recent years. Among these, nonlocal versions of the classical Laplace operator have attracted th…
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…