Postdoc research associate
Office: Wean Hall 7216
Department of Mathematics, Carnegie Mellon University (CMU)
- Jan 2021--- June 2022, Visiting Assistant Professor, Department of Mathematics, Purdue University, Mentor: Prof. Guang Lin.
- PhD, Mathematics, Texas A&M University, Aug 2016 --- Dec 2020.
Prof. Yalchin Efendiev and Prof. Eric Chung.
- M.S., Mathematics, University of Alberta, Aug 2014 --- June 2016.
Directional Splitting On Grid With Local Refinement For Parabolic Problems.|
Prof. Peter Minev
Prof. Yaushu Wong.
- B.S., Applied Mathematics, Hong Kong Baptist University, Aug 2010 --- Jun 2014.
- Multiscale finite element methods
- Inverse problem
- Deep and reinforcement learning
Publications and preprints
- Zecheng Zhang, Wing Tat Leung, Hayden Schaeffer. BelNet: Basis enhanced learning, a mesh-free neural operator. Preprint, 2022.
A tutorial and programming code of BelNet and operator learning is here. This BelNet tutorial is on Kaggle and we will upload a tutorial on GitHub later.
- Guanxun Li, Guang Lin, Zecheng Zhang, Quan Zhou. Fast Tempering for Stochastic Gradient Langevin Dynamics. Preprint, 2022.
- Na Ou, Zecheng Zhang, Guang Lin, A replica exchange preconditioned Crank-Nicolson Langevin
dynamic MCMC method for Bayesian inverse problems. Preprint, 2022.
- Yalchin Efendiev, Wing Tat Leung, Wenyuan Li, Zecheng Zhang. Hybrid explicit-implicit learning for multiscale problems with time dependent source. Communications in Nonlinear Science and Numerical Simulation, 2023.
- Guang Lin, Christian Moya, Zecheng Zhang. On Learning the Dynamical Response of Nonlinear Control Systems with Deep Operator Networks. Preprint, 2022.
- Guang Lin, Zecheng Zhang, Zhidong Zhang. Theoretical and numerical studies of inverse source problem for the linear parabolic equation with sparse boundary measurements. Inverse Problems, 2022.
- Guang Lin, Christian Moya, Zecheng Zhang. Accelerated replica exchange stochastic gradient Langevin diffusion enhanced Bayesian DeepONet for solving noisy parametric PDEs. Journal of Computational Physics, 2022.
- Yalchin Efendiev, Wing Tat Leung, Guang Lin, Zecheng Zhang. Efficient hybrid explicit-implicit learning for multiscale problems. Journal of Computational Physics, 2022.
- Wing Tat Leung, Guang Lin, Zecheng Zhang. NH-PINN: Neural homogenization based the physics-informed neural network for the multiscale problems. Journal of Computational Physics, 2022.
- Guang Lin, Yating Wang, Zecheng Zhang. Multi-variance replica exchange stochastic gradient MCMC for inverse and forward Bayesian physics-informed neural network. Journal of Computational Physics, 2022.
- Liu Liu, Tieyong Zeng, Zecheng Zhang. A deep neural network approach on solving the linear transport model under diffusive scaling. Preprint, 2021.
- Eric Chung, Yalchin Efendiev, Sai-Mang Pun, Zecheng Zhang. Computational multiscale methods for parabolic wave approximations in heterogeneous media. Applied Mathematics and Computation, 2022.
- Eric Chung, Yalchin Efendiev, Wing Tat Leung, Sai-Mang Pun and Zecheng Zhang. Multi-agent reinforcement learning aided sampling algorithms for a class of multiscale inverse problems. Under revision, Journal of Scientific Computing, 2022.
- Boris Chetverushkin, Eric Chung, Yalchin Efendiev, Sai-Mang Pun and Zecheng Zhang. Computational multiscale methods for quasi-gas dynamic equations. Journal of Computational Physics, 2020.
- Eric Chung, Wing Tat Leung, Sai-Mang Pun and Zecheng Zhang. A multi-stage deep learning based algorithm for multiscale model reduction. Journal of Computational and Applied Mathematics, 2020.
- Eric Chung, Yalchin Efendiev, Wing Tat Leung, Zecheng Zhang. Learning Algorithms for Coarsening Uncertainty Space and Applications to Multiscale Simulations. Mathematics, 2020.
Useful Links (construction in progress)