Zhenyu Zhu
9 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Interdisciplinary Bridge
π
Conference Polyglot
(3)
π
Cross-Pollinator
(13)
πΊοΈ
Taxonomy Completionist
(11)
π§
Keyword Pioneer
Conferences
NIPS (5)
ICLR (2)
ICML (2)
Top co-authors
Keywords
neural tangent kernel
(4)
neural network
(3)
generalization bound
(2)
sample complexity
(1)
neural architecture search
(1)
generalization error
(1)
score matching
(1)
score function
(1)
deep neural network
(1)
relu activation
(1)
benign overfitting
(1)
gradient norm
(1)
activation function
(1)
neural network robustness
(1)
spectral bia
(1)
skip connection
(1)
network initialization
(1)
bayes-optimal error
(1)
lazy training
(1)
polynomial neural network
(1)
Papers
How Gradient descent balances features: A dynamical analysis for two-layer neural networks
ICLR 2025
Training Deep Learning Models with Norm-Constrained LMOs
ICML 2025
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
NIPS 2023
Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling
NIPS 2023
Benign Overfitting in Deep Neural Networks under Lazy Training
ICML 2023
Controlling the Complexity and Lipschitz Constant improves Polynomial Nets
ICLR 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
NIPS 2022
Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
NIPS 2022
Generalization Properties of NAS under Activation and Skip Connection Search
NIPS 2022