Libin Zhu - RankMe

20 papers A* 7A 1Journal 11

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	A Hyperspectral Feature Selection Method for Soil Organic Matter Estimation Based on an Improved Weighted Marine Predators Algorithm. IEEE Trans. Geosci. Remote. Sens. Kun Tan, Libin Zhu, Xue Wang
2025	A*	`conf`	Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. ICML Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2025	J	`jnl`	Iteratively reweighted kernel machines efficiently learn sparse functions. CoRR Libin Zhu, Damek Davis, Dmitriy Drusvyatskiy, Maryam Fazel
2024	A*	`conf`	Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. ICML Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024	J	`jnl`	Emergence in non-neural models: grokking modular arithmetic via average gradient outer product. CoRR Neil Mallinar, Daniel Beaglehole, Libin Zhu, Adityanarayanan Radhakrishnan, Parthe Pandit, Mikhail Belkin
2024	A*	`conf`	Quadratic models for understanding catapult dynamics of neural networks. ICLR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2024	—	`—`	Toward Understanding the Dynamics of Over-parameterized Neural Networks Libin Zhu
2023	J	`jnl`	Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning. CoRR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2023	A	`conf`	Neural tangent kernel at initialization: linear width suffices. UAI Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2023	A*	`conf`	Restricted Strong Convexity of Deep Learning Models with Smooth Activations. ICLR Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2022	J	`jnl`	A note on Linear Bottleneck networks and their Transition to Multilinearity. CoRR Libin Zhu, Parthe Pandit, Mikhail Belkin
2022	J	`jnl`	Quadratic models for understanding neural network dynamics. CoRR Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin
2022	J	`jnl`	Restricted Strong Convexity of Deep Learning Models with Smooth Activations. CoRR Arindam Banerjee, Pedro Cisneros-Velarde, Libin Zhu, Mikhail Belkin
2022	A*	`conf`	Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. NeurIPS Libin Zhu, Chaoyue Liu, Mikhail Belkin
2022	J	`jnl`	Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture. CoRR Libin Zhu, Chaoyue Liu, Mikhail Belkin
2022	A*	`conf`	Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. ICLR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2022	J	`jnl`	Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	A*	`conf`	On the linearity of large non-linear models: when and why the tangent kernel is constant. NeurIPS Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	J	`jnl`	On the linearity of large non-linear models: when and why the tangent kernel is constant. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin
2020	J	`jnl`	Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning. CoRR Chaoyue Liu, Libin Zhu, Mikhail Belkin