Kaifeng Lyu

1. Gradient Descent Maximizes the Margin of Homogeneous Neural Networks
   2019/06/13 by Kaifeng Lyu, Lyu, Kaifeng, Jian Li +1 · 29 citations
   Computer Science · #Stochastic Gradient Optimization Techniques #Domain Adaptation and Few-Shot Learning #Advanced Neural Network Applications
2. DistillSpec: Improving Speculative Decoding via Knowledge Distillation
   2023/10/12 by Yongchao Zhou, Zhou, Yongchao, Kaifeng Lyu +13 · 17 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
3. Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
   2024/02/28 by Kaifeng Lyu, Lyu, Kaifeng, Haoyu Zhao +9 · 15 citations
   Business, Management and Accounting · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Taxation and Legal Issues
4. Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning
   2020/12/17 by Zhiyuan Li, Yuping Luo, Li, Zhiyuan +3 · 9 citations
   Computer Science · Engineering · #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
5. AI-Assisted Generation of Difficult Math Questions
   2024/07/30 by Vedant Shah, Dingli Yu, Shah, Vedant +20 · 3 voices · 9 citations
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Machine Learning (cs.LG) #Mathematics, Computing, and Information Processing #cs.AI #cs.LG
6. RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval
   2024/02/28 by Kaiyue Wen, Xingyu Dang, Wen, Kaiyue +3 · 9 citations
   Computer Science · #Topic Modeling
7. Why (and When) does Local SGD Generalize Better than SGD?
   2023/03/02 by Xinran Gu, Gu, Xinran, Kaifeng Lyu +5 · 1 citation
   Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM #Neural Networks and Applications #Statistical Methods and Inference
8. Weak-to-Strong Generalization Even in Random Feature Networks, Provably
   2025/03/04 by Medvedev, Marko, Kaifeng Lyu, Dingli Yu +8 · 1 citation
   Computer Science · #Face and Expression Recognition #Neural Networks and Applications #Anomaly Detection Techniques and Applications
9. Frontier Language Models Struggle to Copy: Text Can Be Better Viewed in 2D
   2026/07/17 by Haodong Wen, Yiran Zhang, Yingfa Chen +1
   #cs.CL