متابعة
Kaifeng Lyu
Kaifeng Lyu
Princeton University
بريد إلكتروني تم التحقق منه على princeton.edu - الصفحة الرئيسية
عنوان
عدد مرات الاقتباسات
عدد مرات الاقتباسات
السنة
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks‏
K Lyu, J Li‏
2020 International Conference on Learning Representations (ICLR 2020), 2020‏
3602020
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning‏
Z Li, Y Luo, K Lyu‏
2021 International Conference on Learning Representations (ICLR 2021), 2021‏
1532021
Theoretical analysis of auto rate-tuning by batch normalization‏
S Arora, Z Li, K Lyu‏
2019 International Conference on Learning Representations (ICLR 2019), 2019‏
1332019
Learning gradient descent: Better generalization and longer horizons‏
K Lv, S Jiang, J Li‏
34th International Conference on Machine Learning (ICML 2017) 70, 2247-2255, 2017‏
1252017
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias‏
K Lyu, Z Li, R Wang, S Arora‏
35th Conference on Neural Information Processing Systems (NeurIPS 2021), 2021‏
872021
Understanding the generalization benefit of normalization layers: Sharpness reduction‏
K Lyu, Z Li, S Arora‏
36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022‏
822022
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate‏
Z Li, K Lyu, S Arora‏
34th Conference on Neural Information Processing Systems (NeurIPS 2020), 2020‏
782020
DistillSpec: Improving speculative decoding via knowledge distillation‏
Y Zhou, K Lyu, AS Rawat, AK Menon, A Rostamizadeh, S Kumar, JF Kagy, ...‏
2024 International Conference on Learning Representations (ICLR 2024), 2024‏
672024
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms‏
S Malladi, K Lyu, A Panigrahi, S Arora‏
36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022‏
422022
Understanding incremental learning of gradient descent: A fine-grained analysis of matrix sensing‏
J Jin, Z Li, K Lyu, SS Du, JD Lee‏
International Conference on Machine Learning (ICML 2023), 15200-15238, 2023‏
412023
Fine-grained complexity meets IP = PSPACE‏
L Chen, S Goldwasser, K Lyu, GN Rothblum, A Rubinstein‏
30th Annual ACM-SIAM Symposium on Discrete Algorithms (SODA 2019), 1-20, 2019‏
402019
Safety Alignment Should Be Made More Than Just a Few Tokens Deep‏
X Qi, A Panda, K Lyu, X Ma, S Roy, A Beirami, P Mittal, P Henderson‏
The Thirteenth International Conference on Learning Representations, 2025‏
292025
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking‏
K Lyu, J Jin, Z Li, SS Du, JD Lee, W Hu‏
2024 International Conference on Learning Representations (ICLR 2024), 2024‏
272024
Keeping LLMs aligned after fine-tuning: The crucial role of prompt templates‏
K Lyu, H Zhao, X Gu, D Yu, A Goyal, S Arora‏
38th Conference on Neural Information Processing Systems (NeurIPS 2024), 2024‏
262024
Why (and When) does Local SGD Generalize Better than SGD?‏
X Gu, K Lyu, L Huang, S Arora‏
2023 International Conference on Learning Representations (ICLR 2023), 2023‏
262023
RNNs are not Transformers (yet): The key bottleneck on in-context retrieval‏
K Wen, X Dang, K Lyu‏
The Thirteenth International Conference on Learning Representations, 2025‏
192025
The marginal value of momentum for small learning rate SGD‏
R Wang, S Malladi, T Wang, K Lyu, Z Li‏
2024 International Conference on Learning Representations (ICLR 2024), 2024‏
82024
Single-Source Bottleneck Path Algorithm Faster than Sorting for Sparse Graphs‏
R Duan, K Lyu, H Wu, Y Xie‏
45th International Colloquium on Automata, Languages, and Programming (ICALP …, 2018‏
82018
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound‏
A Gupta, N Saunshi, D Yu, K Lyu, S Arora‏
36th Conference on Neural Information Processing Systems (NeurIPS 2022), 2022‏
72022
AI-assisted generation of difficult math questions‏
V Shah, D Yu, K Lyu, S Park, J Yu, Y He, NR Ke, M Mozer, Y Bengio, ...‏
arXiv preprint arXiv:2407.21009, 2024‏
52024
يتعذر على النظام إجراء العملية في الوقت الحالي. عاود المحاولة لاحقًا.
مقالات 1–20