Yingzhi Xia

Brief Bio:

I am a Scientist at the Institute of High Performance Computing (IHPC), A*Star, Singapore. I received my Ph.D. degree at University of Chinese Academy of Sciences and ShanghaiTech University, China in 2022, supervised by Prof. Qifeng Liao. Before that, I received a Bachelor's degree from Northwestern Polytechnical University, Majoring in Mathematics and Applied Mathematics. I am interested in Scientific Machine Learning, especially in inverse modelling, deep generative model, and their application in engineering. From July, 2018 to Jan, 2020, I worked as Research assistant at the Scientific Computing and Artificial Intelligence (SCAI) Laboratory of the University of Notre Dame, USA, supervised by Prof. Nicholas Zabaras.

Research Interests:

Scientific Machine Learning

Inverse problems

Deep Generative model

Uncertainty Quantification

Recent News:

• 2024-08: The paper, "A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface design", accepted by Neural Networks.
• 2024-06: The paper "Multi-Scale Region-Aware Implicit Neural Network for Medical Images Matting", accepted by MICCAI 2024.
• 2023-11: The paper, "A domain-decomposed VAE method for Bayesian inverse problems", accepted by International Journal for Uncertainty Quantification.
• 2023-08: The paper, "VI-DGP: A variational inference method with deep generative prior for solving high-dimensional inverse problems", accepted by Journal of Scientific Computing.
• 2022-11: The paper, "A deep domain decomposition method based on Fourier features", accepted by Journal of Computational and Applied Mathematics.
• 2022-08: The paper, "Bayesian Aerosol Retrieval-Based PM2.5 Estimation through Hierarchical Gaussian Process Models", accepted by Mathematics.
• 2022-01: The paper, "Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems", accepted by Journal of Computational Physics.

Projects:

Activities:

• Journal Reviewer:
  • Journal of Computational Physics
  • journal of Computational and Applied Mathematics
  • Communications in Computational Physics
  • IEEE Access

Selected Publications:

Manna Dai, Yang Jiang, Feng Yang, Joyjit Chattoraj, Yingzhi Xia, Xinxing Xu, Weijiang Zhao, My Ha Dao, Yong Liu. "A surrogate-assisted extended generative adversarial network for parameter optimization in free-form metasurface design", Neural Networks 2024, [NN]
• Yanyu Xu, Yingzhi Xia, Huazhu Fu, Rick Siow Mong Goh, Yong Liu, Xinxing Xu. "Multi-Scale Region-Aware Implicit Neural Network for Medical Images Matting", Medical Image Computing and Computer Assisted Intervention (MICCAI 2024), [MICCAI]
• Yingzhi Xia, Qifeng Liao, Jinglai Li. "VI-DGP: A variational inference method with deep generative prior for solving high-dimensional inverse problems", Journal of Scientific Computing 2023, [JSC]
• Zhihang Xu, Yingzhi Xia, Qifeng Liao. "A domain-decomposed VAE method for Bayesian inverse problems", International Journal for Uncertainty Quantification 2023, [IJUQ]
• Sen Li, Yingzhi Xia, Yu Liu, Qifeng Liao. "A deep domain decomposition method based on Fourier features", Journal of Computational and Applied Mathematics 2023, [JCAM]
• Yingzhi Xia, Nicholas Zabaras. "Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems", Journal of Computational Physics 2022, [JCP]
• Junbo Zhang, Daoji Li, Yingzhi Xia, Yu Liu, Qifeng Liao. "Bayesian Aerosol Retrieval-Based PM2.5 Estimation through Hierarchical Gaussian Process Models", Mathematics 2022, [Mathematics]