Hongru Yang
5 papers · 2023–2025 · 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
Venues
Top co-authors
Research topics
Keywords
neural tangent kernel
(2)
neural network optimization
(2)
generalization bound
(2)
attention mechanism
(2)
gradient flow
(2)
training dynamics
(2)
linear classification
(1)
mixture model
(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)
feature learning
(1)
network pruning
(1)
gradient descent
(1)
rademacher complexity
(1)
Papers
Random Pruning Over-parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis
JMLR 2025
Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow
ICLR 2025
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK
JMLR 2024
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
NeurIPS 2024
On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks
AISTATS 2023