Zhanpeng Zhou
12 papers · 2021–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Conference Polyglot (4) π Cross-Pollinator (12) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (11)
π
Academic Marathon
(5)
π
Grand Slam
π
Triple Crown
β
The Questioner
π
Century Club
(11)
Conferences
ICLR (4)
ICML (4)
AAAI (2)
NIPS (2)
Top co-authors
Keywords
stochastic gradient descent
(1)
feature learning
(1)
neural network training
(1)
game theory
(1)
batch normalization
(1)
image reconstruction
(1)
sharpness-aware minimization
(1)
deep learning
(1)
neural network optimization
(1)
loss landscape
(1)
feature representation
(1)
label noise
(1)
gradient descent
(1)
convolutional neural network
(1)
deep neural network
(1)
adversarial perturbation
(1)
loss function
(1)
implicit bia
(1)
learning dynamics
(1)
linear mode connectivity
(1)
Papers
On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
AAAI 2026
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training
ICLR 2025
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
ICLR 2025
On the Role of Label Noise in the Feature Learning Process
ICML 2025
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
ICML 2025
On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
ICML 2024
Batch Normalization Is Blind to the First and Second Derivatives of the Loss
AAAI 2024
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
ICLR 2024
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
NIPS 2023
Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?
ICLR 2023
Defects of Convolutional Decoder Networks in Frequency Representation
ICML 2023
Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness
NIPS 2021