Scholar

Zhong Li

Google Scholar ID: iPw508sAAAAJ

Microsoft Research Asia

Deep Learning

Citations & Impact

All-time

Citations

230

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

11 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Research Experience

Education

Bachelor's degree from Tang'aoqing Honors Program in Mathematics at Jilin University; PhD degree from School of Mathematical Sciences at Peking University, supervised by Prof. Weinan E.

Background

Research interests center around the mathematical theories, principles, and algorithms of deep learning, including: Theoretical foundations of neural networks; The approximation, optimization, and generalization analysis of inductive biases of NNs, particularly for seq2seq/time-series modeling (e.g., RNNs, CNNs, encoder-decoders, transformers, etc.); Data-dependent development of machine learning; Mathematics and principles of AIGC; Theories and algorithms of diffusion models; Data-efficient learning, with the application to large language models.

Miscellany

Always seeking highly self-motivated research interns with solid mathematical foundations and skilled coding techniques. If interested in theories (at least, principles) of machine learning and LLMs, feel free to contact via email lzhong@microsoft.com.

Co-authors

11 total