activity
20242026
most citedGenAI4UQ: A Software for Inverse Uncertainty Quantification Using Conditional Generative Models

1 citations · 1 across the 5 of their papers we have counts for

collaborators

5 papers

math.NA2026

Error estimates of a training-free diffusion model for high-dimensional sampling

Pengjun Wang, Zezhong Zhang, Minglei Yang +3

Score-based diffusion models are a powerful class of generative models, but their practical use often depends on training neural networks to approximate the score function. Trainin…

cs.CE2025

Exact Conditional Score-Guided Generative Modeling for Amortized Inference in Uncertainty Quantification

Zezhong Zhang, Caroline Tatsuoka, Dongbin Xiu +1

We propose an efficient framework for amortized conditional inference by leveraging exact conditional score-guided diffusion models to train a non-reversible neural network as a co…

stat.ML2025

Diffusion-based supervised learning of generative models for efficient sampling of multimodal distributions

Hoang Tran, Zezhong Zhang, Feng Bao +2

We propose a hybrid generative model for efficient sampling of high-dimensional, multimodal probability distributions for Bayesian inference. Traditional Monte Carlo methods, such…

cs.LG20241 cited

GenAI4UQ: A Software for Inverse Uncertainty Quantification Using Conditional Generative Models

Ming Fan, Zezhong Zhang, Dan Lu +1

We introduce GenAI4UQ, a software package for inverse uncertainty quantification in model calibration, parameter estimation, and ensemble forecasting in scientific applications. Ge…

cs.LG2024

Nonuniform random feature models using derivative information

Konstantin Pieper, Zezhong Zhang, Guannan Zhang

We propose nonuniform data-driven parameter distributions for neural network initialization based on derivative data of the function to be approximated. These parameter distributio…