Hongru Yang
5 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(4)
🐝
Cross-Pollinator
(9)
Conferences
JMLR (2)
AISTATS (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
neural tangent kernel
(2)
training dynamics
(2)
neural network optimization
(2)
generalization bound
(2)
gradient descent
(1)
rademacher complexity
(1)
gradient flow
(1)
sparse activation
(1)
relu network
(1)
bias initialization
(1)
random pruning
(1)
neural network
(1)
neural network pruning
(1)
infinite-width analysis
(1)
representation learning
(1)
attention mechanism
(1)
network pruning
(1)
Papers
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
ICLR 2025
Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis
JMLR 2025
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
NIPS 2024
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK
JMLR 2024
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks
AISTATS 2023