About me
I am currently an IFDS postdoc scholar at the University of Washington, working with Dmitriy Drusvyatskiy and Maryam Fazel. I received my PhD in Computer Science from UCSD, where I was fortunate to be advised by Mikhail Belkin. Prior to UCSD, I received my BS in Mathematics from Zhejiang University.
I am broadly interested in the optimization and mathematical foundations of deep learning. I have worked on understanding the dynamics of wide neural networks, particularly in the NTK [Jacot et al. 2018] regime and catapult [Lewkowycz et al. 2020] regime. More recently, I have focused on feature learning in machine learning models, particularly in neural networks and kernel machines.
Email: libinzhu at uw dot edu
Selected Papers
- L Zhu, D Davis, D Drusvyatskiy, M Fazel, Iteratively reweighted kernel machines efficiently learn sparse functions. Pre-printed.
- N Mallinar, D Beaglehole, L Zhu, A Radhakrishnan, P Pandit, M Belkin, Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. ICML 2025.
- L Zhu, C Liu, A Radhakrishnan, M Belkin, Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. ICML 2024.
- L Zhu, C Liu, A Radhakrishnan, M Belkin, Quadratic models for understanding catapult dynamics of neural networks. ICLR 2024.
- L Zhu, C Liu, M Belkin, Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. NeurIPS 2022.
- C Liu, L Zhu, M Belkin, On the linearity of large non-linear models: when and why the tangent kernel is constant. NeurIPS 2020 (Spotlight).
- C Liu, L Zhu, M Belkin, Loss landscapes and optimization in over-parameterized non-linear systems and neural networks. Applied and Computational Harmonic Analysis (ACHA) 2022.