Denny Wu
~Denny_Wu2
12
论文总数
6.0
年均投稿
平均评分
接收情况11/12
会议分布
NeurIPS
7
ICLR
3
ICML
2
发表论文 (12 篇)
20259 篇
4
Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
ICLR 2025Poster
3
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
ICML 2025Poster
4
Emergence and scaling laws in SGD learning of shallow neural networks
NeurIPS 2025Poster
4
When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
NeurIPS 2025Poster
3
Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
NeurIPS 2025Poster
4
Nonlinear transformers can perform inference-time feature learning
ICML 2025Poster
5
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
NeurIPS 2025Poster
5
Label Noise Gradient Descent Improves Generalization in the Low SNR Regime
ICLR 2025Rejected
5
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
NeurIPS 2025Spotlight
20243 篇
4
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
NeurIPS 2024Poster
3
Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
ICLR 2024Poster
4
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
NeurIPS 2024Poster