default search action
Kaifeng Lyu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [c16]Xinran Gu, Kaifeng Lyu, Sanjeev Arora, Jingzhao Zhang, Longbo Huang:
A Quadratic Synchronization Rule for Distributed Deep Learning. ICLR 2024 - [c15]Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon Shaolei Du, Jason D. Lee, Wei Hu:
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. ICLR 2024 - [c14]Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li:
The Marginal Value of Momentum for Small Learning Rate SGD. ICLR 2024 - [c13]Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, Rishabh Agarwal:
DistillSpec: Improving Speculative Decoding via Knowledge Distillation. ICLR 2024 - [i21]Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu, Sobhan Miryoosefi, Sashank J. Reddi, Satyen Kale, Sanjiv Kumar:
Efficient Stagewise Pretraining via Progressive Subnetworks. CoRR abs/2402.05913 (2024) - [i20]Kaiyue Wen, Xingyu Dang, Kaifeng Lyu:
RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval. CoRR abs/2402.18510 (2024) - [i19]Kaifeng Lyu, Haoyu Zhao, Xinran Gu, Dingli Yu, Anirudh Goyal, Sanjeev Arora:
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates. CoRR abs/2402.18540 (2024) - [i18]Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson:
Safety Alignment Should Be Made More Than Just a Few Tokens Deep. CoRR abs/2406.05946 (2024) - [i17]Vedant Shah, Dingli Yu, Kaifeng Lyu, Simon Park, Nan Rosemary Ke, Michael Mozer, Yoshua Bengio, Sanjeev Arora, Anirudh Goyal:
AI-Assisted Generation of Difficult Math Questions. CoRR abs/2407.21009 (2024) - 2023
- [c12]Xinran Gu, Kaifeng Lyu, Longbo Huang, Sanjeev Arora:
Why (and When) does Local SGD Generalize Better than SGD? ICLR 2023 - [c11]Jikai Jin, Zhiyuan Li
, Kaifeng Lyu, Simon Shaolei Du, Jason D. Lee:
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. ICML 2023: 15200-15238 - [i16]Jikai Jin, Zhiyuan Li, Kaifeng Lyu, Simon S. Du, Jason D. Lee:
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing. CoRR abs/2301.11500 (2023) - [i15]Xinran Gu, Kaifeng Lyu, Longbo Huang, Sanjeev Arora:
Why (and When) does Local SGD Generalize Better than SGD? CoRR abs/2303.01215 (2023) - [i14]Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li
The Marginal Value of Momentum for Small Learning Rate SGD. CoRR abs/2307.15196 (2023) - [i13]Yongchao Zhou, Kaifeng Lyu, Ankit Singh Rawat, Aditya Krishna Menon, Afshin Rostamizadeh, Sanjiv Kumar, Jean-François Kagy, Rishabh Agarwal:
DistillSpec: Improving Speculative Decoding via Knowledge Distillation. CoRR abs/2310.08461 (2023) - [i12]Xinran Gu, Kaifeng Lyu, Sanjeev Arora, Jingzhao Zhang, Longbo Huang:
A Quadratic Synchronization Rule for Distributed Deep Learning. CoRR abs/2310.14423 (2023) - [i11]Kaifeng Lyu, Jikai Jin, Zhiyuan Li
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking. CoRR abs/2311.18817 (2023) - 2022
- [c10]Arushi Gupta, Nikunj Saunshi, Dingli Yu, Kaifeng Lyu, Sanjeev Arora:
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound. NeurIPS 2022 - [c9]Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora:
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction. NeurIPS 2022 - [c8]Sadhika Malladi, Kaifeng Lyu, Abhishek Panigrahi, Sanjeev Arora:
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms. NeurIPS 2022 - [i10]Sadhika Malladi, Kaifeng Lyu, Abhishek Panigrahi, Sanjeev Arora:
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms. CoRR abs/2205.10287 (2022) - [i9]Kaifeng Lyu, Zhiyuan Li, Sanjeev Arora:
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction. CoRR abs/2206.07085 (2022) - [i8]Arushi Gupta, Nikunj Saunshi, Dingli Yu, Kaifeng Lyu, Sanjeev Arora:
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound. CoRR abs/2211.02912 (2022) - 2021
- [c7]Zhiyuan Li
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning. ICLR 2021 - [c6]Kaifeng Lyu, Zhiyuan Li
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias. NeurIPS 2021: 12978-12991 - [i7]Kaifeng Lyu, Zhiyuan Li, Runzhe Wang, Sanjeev Arora:
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias. CoRR abs/2110.13905 (2021) - 2020
- [c5]Kaifeng Lyu, Jian Li:
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks. ICLR 2020 - [c4]Zhiyuan Li
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate. NeurIPS 2020 - [i6]Zhiyuan Li, Kaifeng Lyu, Sanjeev Arora:
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate. CoRR abs/2010.02916 (2020) - [i5]Zhiyuan Li, Yuping Luo, Kaifeng Lyu:
Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning. CoRR abs/2012.09839 (2020)
2010 – 2019
- 2019
- [c3]Sanjeev Arora, Zhiyuan Li
Theoretical Analysis of Auto Rate-Tuning by Batch Normalization. ICLR (Poster) 2019 - [c2]Lijie Chen, Shafi Goldwasser, Kaifeng Lyu, Guy N. Rothblum, Aviad Rubinstein:
Fine-grained Complexity Meets IP = PSPACE. SODA 2019: 1-20 - [i4]Kaifeng Lyu, Jian Li:
Gradient Descent Maximizes the Margin of Homogeneous Neural Networks. CoRR abs/1906.05890 (2019) - 2018
- [c1]Ran Duan, Kaifeng Lyu, Yuanhang Xie:
Single-Source Bottleneck Path Algorithm Faster than Sorting for Sparse Graphs. ICALP 2018: 43:1-43:14 - [i3]Lijie Chen, Shafi Goldwasser, Kaifeng Lyu, Guy N. Rothblum, Aviad Rubinstein:
Fine-grained Complexity Meets IP = PSPACE. CoRR abs/1805.02351 (2018) - [i2]Ran Duan, Kaifeng Lyu, Hongxun Wu, Yuanhang Xie:
Single-Source Bottleneck Path Algorithm Faster than Sorting for Sparse Graphs. CoRR abs/1808.10658 (2018) - [i1]Sanjeev Arora, Zhiyuan Li, Kaifeng Lyu:
Theoretical Analysis of Auto Rate-Tuning by Batch Normalization. CoRR abs/1812.03981 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-07 21:23 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: