52 citations · 59 across the 13 of their papers we have counts for
14 papers
Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO Scheme
Chenguang Duan, Johannes Hertrich, Gabriele Steidl
We propose a neural algorithm for sampling from distributions specified by unnormalized Boltzmann densities. Our approach is based on the Jordan--Kinderlehrer--Otto scheme for the…
Diffusion Based Unpaired Data Learning for Inverse Problems
Chenglong Bao, Yiming Dang, Chenguang Duan +2
Data is important in many deep learning-based inverse problem solvers. However, obtaining sufficient paired data in many scenarios remains highly challenging, while unpaired data i…
Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
Jinyuan Chang, Chenguang Duan, Yuling Jiao +2
Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, the…
Preconditioning and Numerical Stability in Neural Network Training for Parametric PDEs
Markus Bachmayr, Wolfgang Dahmen, Chenguang Duan +1
In the context of training neural network-based approximations of solutions of parameter-dependent PDEs, we investigate the effect of preconditioning via well-conditioned frame rep…
Sampling via Stochastic Interpolants by Langevin-based Velocity and Initialization Estimation in Flow ODEs
Chenguang Duan, Yuling Jiao, Gabriele Steidl +3
We propose a novel method for sampling from unnormalized Boltzmann densities based on a probability flow ordinary differential equation (ODE) derived from linear stochastic interpo…
Provable Diffusion Posterior Sampling for Bayesian Inversion
Jinyuan Chang, Chenguang Duan, Yuling Jiao +3
We propose a novel diffusion-based posterior sampling method within a plug-and-play framework. Our approach constructs a probability transport from an easy-to-sample distribution t…
Nonlinear Assimilation via Score-based Sequential Langevin Sampling
Zhao Ding, Chenguang Duan, Yuling Jiao +3
This paper introduces score-based sequential Langevin sampling (SSLS), a novel approach to nonlinear data assimilation within a recursive Bayesian filtering framework. The proposed…
Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
Chenguang Duan, Yuling Jiao, Huazhen Lin +2
Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have bee…
Characteristic Learning for Provable One Step Generation
Zhao Ding, Chenguang Duan, Yuling Jiao +3
We propose the characteristic generator, an one-step generative model that combines the sampling efficiency of generative adversarial networks (GANs) with the training stability of…
Semi-Supervised Deep Sobolev Regression: Estimation and Variable Selection by ReQU Neural Network
Zhao Ding, Chenguang Duan, Yuling Jiao +1
We propose SDORE, a Semi-supervised Deep Sobolev Regressor, for the nonparametric estimation of the underlying regression function and its gradient. SDORE employs deep ReQU neural…
Current density impedance imaging with PINNs
Chenguang Duan, Yuling Jiao, Xiliang Lu +1
In this paper, we introduce CDII-PINNs, a computationally efficient method for solving CDII using PINNs in the framework of Tikhonov regularization. This method constructs a physic…
Deep Neural Network Approximation of Composition Functions: with application to PINNs
Chenguang Duan, Yuling Jiao, Xiliang Lu +2
In this paper, we focus on approximating a natural class of functions that are compositions of smooth functions. Unlike the low-dimensional support assumption on the covariate, we…
Analysis of Deep Ritz Methods for Laplace Equations with Dirichlet Boundary Conditions
Chenguang Duan, Yuling Jiao, Yanming Lai +3
Deep Ritz methods (DRM) have been proven numerically to be efficient in solving partial differential equations. In this paper, we present a convergence rate in norm for dee…
Convergence Rate Analysis for Deep Ritz Method
Chenguang Duan, Yuling Jiao, Yanming Lai +2
Using deep neural networks to solve PDEs has attracted a lot of attentions recently. However, why the deep learning method works is falling far behind its empirical success. In thi…