Scholar
Mingze Wang
Google Scholar ID: CkU47X0AAAAJ
School of Mathematical Sciences, Peking University
Citations & Impact
Citations
194
H-index
9
i10-index
7
Publications
18
Co-authors
6
list available
Contact
Publications
Resume (English only)
Academic Achievements
- 2025: Awarded the ByteDance Scholarship (20 recipients across China and Singapore)
- 2025: Paper accepted to NeurIPS 2025 as Spotlight (top 3.5%)
- 2025: Paper accepted to ICLR 2025 as Spotlight (top 5.1%)
- 2024: Supported by the Young Scientists (Ph.D.) Fund of the National Natural Science Foundation of China (Project: Analyzing and Improving the Adam Optimizer for Foundation Model Training)
- 2024: Recipient of China National Scholarship (top 0.2% nationwide)
- 2024: Three papers accepted to NeurIPS 2024; one to ICML 2024; one to ACL 2024
- 2023: Awarded the BICMR Mathematical Award for Graduate Students (top 1%)
- 2023: Paper accepted to NeurIPS 2023 as Spotlight (top 3.5%)
- 2022: Passed Ph.D. qualifying exam
- 2022: Received PKU Academic Innovation Award (top 1%)
- 2022: Two papers accepted to NeurIPS 2022
Background
- Final-year Ph.D. candidate in Computational Mathematics, School of Mathematical Sciences, Peking University (2021–Present)
- Broadly interested in theory, algorithm, and application of machine learning
- Also interested in non-convex and convex optimization
- Recently dedicated to using theory to design algorithms elegantly
- Specific research topics include: Deep Learning Theory (expressivity, optimization, generalization, implicit bias); Transformers and Large Language Models (theory and algorithms, especially in pre-training); Non-convex and Convex Optimization (theory and algorithms)
