Scholar
Yiping Lu
Google Scholar ID: NmhvVBgAAAAJ
Assistant Professor, Northwestern University
Citations & Impact
Citations
3,573
H-index
14
i10-index
15
Publications
20
Co-authors
33
list available
Publications
Resume (English only)
Academic Achievements
- Recipient of the 2024 Conference on Parsimony and Learning (CPAL) Rising Star Award, 2022 Rising Star in Data Science from the University of Chicago, 2021 Stanford Interdisciplinary Graduate Fellowship, and 2019 SenseTime Scholarship. Served as Area Chair for top machine learning conferences such as ICML, Neurips, and AISTATS. Recent research projects include the first principle of the MUON optimizer, theory-inspired and physics-informed inference time scaling, hybrid numerical analysis and ML applications, statistical analysis of scaling law, multiscale structure of gradient descent, and LLM agents for math.
Research Experience
- Currently a tenure-track assistant professor at the Department of Industrial Engineering & Management Science, Northwestern University. Previously, worked as a Courant instructor at the Courant Institute of Mathematical Sciences, New York University for one year.
Education
- Received a Bachelor's degree in Applied Mathematics from Peking University in 2019 and a Ph.D. in Applied Mathematics from Stanford University in 2023. The advisor during the Ph.D. period is unknown.
Background
- Research Interests: Statistical Learning Theory, Deep Learning Theory, Functional Analysis, Kernel Operator and Approximation Theory, Stochastic Simulation, Monte Carlo Methods, Stochastic Control, Optimal Transport, Robust Machine Learning, Uncertainty Estimation, Model Calibration. Applications: Scientific Machine Learning, AI4Science (Scaling Law, Hybrid Methods, etc.), Diffusion Process (Simulation-Free Methods for Control), Foundation Models.
Miscellany
- Happy to host (remote) undergraduate/graduate visitors and looking for Ph.D. students and postdocs. Information available for prospective summer interns for 2025. Welcomes any (anonymous) feedback.
