Introduction

POSITION/TITLE

SRIBD Research Scientist

RESEARCH FIELD

Optimization, Deep Learning Theory

EMAIL

dingtian@sribd.cn

EDUCATION BACKGROUND

MPhil & PhD in Information Engineering - Chinese University of Hong Kong

BS in Automation – Tsinghua University

BIOGRAPHY

Dr. Tian Ding is currently a research scientist in SRIBD. He received his Ph.D. in Information Engineering from the Chinese University of Hong Kong in 2019. His research spans various fields such as optimization theory & algorithm and deep learning theory, including landscape theory of deep learning, network planning and optimization, and large language models. Dr. Ding was a researcher at the Theory Lab of Huawei Central Research Institute.

ACADEMIC PUBLICATIONS

• B. Li, L. Yang, Y. Chen, S. Wang, Q. Chen, H. Mao, Y. Ma, A. Wang, T. Ding, J. Tang, R. Sun, “PDHG-unrolled learning-to-optimize method for large-scale linear programming”, ICML 2024.
• T. Ding, D. Li, R. Sun, “Suboptimal local minima exist for wide neural networks with smooth activations”, Mathematics of Operations Research, 2022.
• D. Li, T. Ding, R. Sun, “On the benefit of width for neural networks: Disappearance of basins”, SIAM Journal on Optimization, 2022.
• T. Ding, X. Yuan, and S. C. Liew, “Sparsity learning based multiuser detection in massive-device multiple access”, IEEE Transactions on Wireless Communications, Jul. 2019.
• T. Ding, X. Yuan, and S. C. Liew, “On the degrees of freedom of the symmetric multi-relay MIMO Y channel”, IEEE Transactions on Wireless Communications, Sep. 2017.