Scholar
Libin Zhu
Google Scholar ID: hyTGiUcAAAAJ
University of Washington
Citations & Impact
Citations
775
H-index
7
i10-index
7
Publications
13
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Selected Papers:
- - 'Iteratively reweighted kernel machines efficiently learn sparse functions', Preprinted.
- - 'Emergence in non-neural models: grokking modular arithmetic via average gradient outer product', ICML 2025 (Oral).
Research Experience
- Currently an IFDS postdoc fellow at the University of Washington, working with Dmitriy Drusvyatskiy and Maryam Fazel.
Education
- PhD: Computer Science from UCSD, advised by Mikhail Belkin; BS: Mathematics from Zhejiang University.
Background
- Research Interests: optimization and mathematical foundations of machine learning. Research focuses on understanding the dynamics of over-parameterized neural networks, particularly in the Neural Tangent Kernel (NTK) and feature learning regimes.
Miscellany
- Currently on the job market for full-time positions.
