Skip to content

Libin Zhu

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

6

Venues

3

Active years

2022–2025

Best venue rank

A*

Where they publish

Papers

6 indexed papers, newest first.

YearVenueTitleAuthors
2025ICMLEmergence in non-neural models: grokking modular arithmetic via average gradient outer product.Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2024ICLRQuadratic models for understanding catapult dynamics of neural networks.Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024ICMLCatapults in SGD: spikes in the training loss and their impact on generalization through feature learning.Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2023ICLRRestricted Strong Convexity of Deep Learning Models with Smooth Activations.Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2023UAINeural tangent kernel at initialization: linear width suffices.Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2022ICLRTransition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models.Chaoyue Liu, Libin Zhu, Mikhail Belkin