Libin Zhu
8 papers · 2020–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
neural tangent kernel
(4)
neural network
(3)
gradient descent
(3)
neural network optimization
(2)
transition to linearity
(2)
quadratic models
(1)
restricted strong convexity
(1)
hessian matrix
(1)
geometric convergence
(1)
modular arithmetic
(1)
directed acyclic graph
(1)
batch size
(1)
infinite width
(1)
network initialization
(1)
network width
(1)
wide neural network
(1)
feedforward neural network
(1)
eigenvalue bound
(1)
smooth activation function
(1)
lazy training
(1)
Papers
Emergence in non-neural models: grokking modular arithmetic via average gradient outer product
ICML 2025
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning
ICML 2024
Quadratic models for understanding catapult dynamics of neural networks
ICLR 2024
Neural tangent kernel at initialization: linear width suffices
UAI 2023
Restricted Strong Convexity of Deep Learning Models with Smooth Activations
ICLR 2023
Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture
NeurIPS 2022
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models
ICLR 2022
On the linearity of large non-linear models: when and why the tangent kernel is constant
NeurIPS 2020