Center for Stochastic Dynamics
Department of Applied Mathematics
Illinois Institute of Technology
Chicago, IL 60616
Office: RE 115B
My research interests include Scientific Machine Learning (PINN, PIGP, Probabilisty Numerics, etc.), Inverse Problems, Data Recovery, Image/Signal Processing, Numerical ODE/PDE, Modeling and Simulation. In particular, I develop and analyze scientific machine learning algorithms for making knowledge/model discoveries from observation data. These algorithms are convergence, efficient (able to able to handle big data, with roughly linear run time), and effective (application to a wide range of situations).
- Physics Informed Machine Learning for solving and learning various PDEs (Talk1 on YouTube, Talk2 on YouTube)
- Learning Self Organization from Observations (See the 2022 AMS Gibbs Lecture on Self Organization)
- Numerical PDEs, especially central schemes for hyperbolic conservation laws
- Computation of Optimal Transport Plan
- Geometric Numerical Integrators
- Parallel and GPU Computing (MPI, openMP, CUDA)
One fully funded Ph.D. (with research assistantshp) position is avaiable in my group. Interested students should apply through the official IIT page.
Before moving to Illinois Tech, I was an assistant research scientist in the Texas A&M Institute of Data Science working with Prof. U. Braga-Neto, Prof. S. Foucart, and Prof. L. Wang on the algorithmic and theoretic development and applications of Scientific Machine Learning. And before my position at TAMU, I was a postdoc fellow at Johns Hopkins University working with Prof. M. Maggioni on various projects which combine machine learning and dynamical systems together to study collective behaviors (clustering, flocking, milling, etc.) from observation data. I obtained my Ph.D. in Applied Mathematics, under the guidance of Prof. E. Tadmor.