Guannan Zhang, Ph.D. - Research Highlights

Research Highlights

Machine Learning and Artificial Intelligence

PI3NN: Out-of-distribution-aware prediction intervals from three neural networks

Learning nonlinear level sets for dimensionality reduction in function approximation

A Nonlocal Gradient for High-Dimensional Blackbox Optimization

Accelerating Reinforcement Learning with a Directional-Gaussian-Smoothing Evolution Strategy

A stochastic approximate gradient ascent method for Bayesian experimental design with implicit models

AdaDGS: An adaptive black-box optimization method with a nonlocal directional Gaussian smoothing gradient

Non-intrusive inference reduced order model for fluids using deep multistep neural network

Training-free diffusion model for supervised learning of generative AI models

Diffusion models for nonlinear data assimilation

Partial Differential Equations and Dynamical Systems

Numerical integration of stiff stochastic chemical systems

Domain decomposition model reduction for convection diffusion equations with random coefficients

Quasi-optimal polynomial approximation for parametric PDEs

Lebesgue constant of weighted Leja points for Lagrange interpolation

Discrete-least-squares reduced-basis methods for parametric PDEs

Backward SDEs driven by jump processes

Hyperspherical sparse approximation for high-dimensional discontinuity detection

A mesh-free implicit filter method for nonlinear filtering problems

Probabilistic numerical schemes for nonlinear local and nonlocal PDEs

Scientific and Engineering Applications

A backward Monte-Carlo method for runaway electron dynamics in fusion tokamaks

A sparse-grid probabilistic scheme for approximation of the runaway probability of electrons in fusion tokamak simulation

A Feynman-Kac based numerical method for the exit time probability of a class of transport problems in plasma physics

A directional Gaussian smoothing optimization method for computational inverse design in nanophotonics

Scalable Machine-Learning-based Optimal Design for Additively Manufactured Materials

Black-box optimization for heat transfer calculations in metal additive manufacturing

Model Calibration of the Liquid Mercury Spallation Target at SNS

Machine-Learning-Assisted Automation of Single Crystal Neutron Diffraction

Atomic Resolution Cryogenic 4D-STEM Imaging via Robust Distortion Correction

A scalable transformer model for real-time decision making in neutron scattering experiments

Rapid optimization of crystal field Hamiltonian

Google Sites

Report abuse