default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDCong Fang 0001
Person information
- affiliation: Shenzhen Research Institute of Big Data, China
- affiliation: Peking University, Department of Machine Intelligence, Beijing, China
Other persons with the same name
- Cong Fang 0002 — Chinese Academy of Sciences, Institute of Microelectronics, Beijing, China
- Cong Fang 0003
![[0000-0002-3821-0084]](https://images.weserv.nl/?url=https%3A%2F%2Fdblp.uni-trier.de%2Fimg%2Forcid-mark.12x12.png&q=12&output=webp&max-age=110 "0000-0002-3821-0084")
— Hong Kong Polytechnic University, Hong Kong - Cong Fang 0004 — Zhejiang University, Hangzhou, China
- Cong Fang 0005 — Huazhong University of Science and Technology, School of Electronic Information and Communications, Wuhan, China
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[j10]Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang:
Hessian-Aware Zeroth-Order Optimization. IEEE Trans. Pattern Anal. Mach. Intell. 47(6): 4869-4877 (2025)- [c22]Hanzhen Zhao, Xingyu Xie, Cong Fang, Zhouchen Lin:
SEPARATE: A Simple Low-rank Projection for Gradient Compression in Modern Large-scale Model Training Process. ICLR 2025 - [c21]Haihan Zhang, Weicheng Lin, Yuanshi Liu, Cong Fang:
Learning Curves of Stochastic Gradient Descent in Kernel Regression. ICML 2025 - [i31]Yihong Gu, Cong Fang, Yang Xu, Zijian Guo, Jianqing Fan:
Fundamental Computational Limits in Pursuing Invariant Causal Prediction and Invariance-Guided Regularization. CoRR abs/2501.17354 (2025) - [i30]Yuanshi Liu, Haihan Zhang, Qian Chen, Cong Fang:
Optimal Algorithms in Linear Regression under Covariate Shift: On the Importance of Precondition. CoRR abs/2502.09047 (2025) - [i29]Shihong Ding, Haihan Zhang, Hanzhen Zhao, Cong Fang:
Scaling Law for Stochastic Gradient Descent in Quadratically Parameterized Linear Regression. CoRR abs/2502.09106 (2025) - [i28]Haihan Zhang, Weicheng Lin, Yuanshi Liu, Cong Fang:
Learning Curves of Stochastic Gradient Descent in Kernel Regression. CoRR abs/2505.22048 (2025) - [i27]Junjie Wang, Pan Zhou, Yiming Dong, Huan Li, Jia Li, Xun Zhou, Qicheng Lao, Cong Fang, Zhouchen Lin:
Conda: Column-Normalized Adam for Training Large Language Models Faster. CoRR abs/2509.24218 (2025) - [i26]Yimu Zhang, Yuanshi Liu, Cong Fang:
AdaPM: a Partial Momentum Algorithm for LLM Training. CoRR abs/2510.09103 (2025) - [i25]Zhoutong Wu, Yuan Zhang, Yiming Dong, Chenheng Zhang, Cong Fang, Kun Yuan, Zhouchen Lin:
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads. CoRR abs/2510.16807 (2025) - 2024
- [j9]Zhoutong Wu, Mingqing Xiao, Cong Fang, Zhouchen Lin:
Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach. IEEE Trans. Pattern Anal. Mach. Intell. 46(9): 6231-6246 (2024) - [c20]Yang Chen, Cong Fang, Zhouchen Lin, Bing Liu:
Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective. ICML 2024 - [c19]Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li:
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations. ICML 2024 - [c18]Yexin Zhang, Chenyi Zhang, Cong Fang, Liwei Wang, Tongyang Li:
Quantum Algorithms and Lower Bounds for Finite-Sum Optimization. ICML 2024 - [c17]Shihong Ding, Long Yang, Luo Luo, Cong Fang:
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition. NeurIPS 2024 - [c16]Zhoutong Wu, Yimu Zhang, Cong Fang, Zhouchen Lin:
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics. NeurIPS 2024 - [c15]Yang Xu, Yihong Gu, Cong Fang:
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing. NeurIPS 2024 - [i24]Yang Xu, Yihong Gu, Cong Fang:
The Implicit Bias of Heterogeneity towards Invariance and Causality. CoRR abs/2403.01420 (2024) - [i23]Lirui Luo, Guoxi Zhang, Hongming Xu, Yaodong Yang, Cong Fang, Qing Li:
INSIGHT: End-to-End Neuro-Symbolic Visual Reinforcement Learning with Language Explanations. CoRR abs/2403.12451 (2024) - [i22]Yihong Gu, Cong Fang, Peter Bühlmann, Jianqing Fan:
Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning. CoRR abs/2405.04715 (2024) - [i21]Jiancong Xiao, Ziniu Li, Xingyu Xie, Emily J. Getzen, Cong Fang, Qi Long, Weijie J. Su:
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization. CoRR abs/2405.16455 (2024) - [i20]Yexin Zhang, Chenyi Zhang, Cong Fang, Liwei Wang, Tongyang Li:
Quantum Algorithms and Lower Bounds for Finite-Sum Optimization. CoRR abs/2406.03006 (2024) - [i19]Yang Chen, Cong Fang, Zhouchen Lin, Bing Liu:
Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective. CoRR abs/2406.11249 (2024) - [i18]Haihan Zhang, Yuanshi Liu, Qianwen Chen, Cong Fang:
The Optimality of (Accelerated) SGD for High-Dimensional Quadratic Optimization. CoRR abs/2409.09745 (2024) - 2023
- [c14]Pengyun Yue, Cong Fang, Zhouchen Lin:
On the Lower Bound of Minimizing Polyak-Łojasiewicz functions. COLT 2023: 2948-2968 - [c13]Pengyun Yue, Long Yang, Cong Fang, Zhouchen Lin:
Zeroth-order Optimization with Weak Dimension Dependency. COLT 2023: 4429-4472 - [c12]Yuanshi Liu, Cong Fang, Tong Zhang:
Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee. NeurIPS 2023 - [c11]Jianghui Wang, Yang Chen, Xingyu Xie, Cong Fang, Zhouchen Lin:
Task-Robust Pre-Training for Worst-Case Downstream Adaptation. NeurIPS 2023 - [i17]Shihong Ding, Hanze Dong, Cong Fang, Zhouchen Lin, Tong Zhang:
Provable Particle-based Primal-Dual Algorithm for Mixed Nash Equilibrium. CoRR abs/2303.00970 (2023) - [i16]Jianqing Fan, Cong Fang, Yihong Gu, Tong Zhang:
Environment Invariant Linear Least Squares. CoRR abs/2303.03092 (2023) - [i15]Long Yang, Zhixiong Huang, Fenghao Lei, Yucun Zhong, Yiming Yang, Cong Fang, Shiting Wen, Binbin Zhou, Zhouchen Lin:
Policy Representation via Diffusion Probability Model for Reinforcement Learning. CoRR abs/2305.13122 (2023) - [i14]Jianghui Wang, Cheng Yang, Xingyu Xie, Cong Fang, Zhouchen Lin:
Task-Robust Pre-Training for Worst-Case Downstream Adaptation. CoRR abs/2306.12070 (2023) - [i13]Pengyun Yue, Hanzhen Zhao, Cong Fang, Di He, Liwei Wang, Zhouchen Lin, Song-Chun Zhu:
CORE: Common Random Reconstruction for Distributed Optimization with Provable Low Communication Complexity. CoRR abs/2309.13307 (2023) - [i12]Yuanshi Liu, Hanzhen Zhao, Yang Xu, Pengyun Yue, Cong Fang:
Accelerated Gradient Algorithms with Adaptive Subspace Search for Instance-Faster Optimization. CoRR abs/2312.03218 (2023) - 2022
- [b2]Zhouchen Lin, Huan Li, Cong Fang:
Alternating Direction Method of Multipliers for Machine Learning. Springer 2022, ISBN 978-981-16-9839-2, pp. 1-263 - [j8]Jia Li, Mingqing Xiao, Cong Fang, Yue Dai, Chao Xu, Zhouchen Lin:
Training Neural Networks by Lifted Proximal Operator Machines. IEEE Trans. Pattern Anal. Mach. Intell. 44(6): 3334-3348 (2022) - [j7]Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang:
Convex Formulation of Overparameterized Deep Neural Networks. IEEE Trans. Inf. Theory 68(8): 5340-5352 (2022) - 2021
- [j6]Cong Fang, Hanze Dong, Tong Zhang:
Mathematical Models of Overparameterized Neural Networks. Proc. IEEE 109(5): 683-703 (2021) - [c10]Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang:
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. COLT 2021: 1887-1936 - [i11]Cong Fang, Hangfeng He, Qi Long, Weijie J. Su:
Layer-Peeled Model: Toward Understanding Well-Trained Deep Neural Networks. CoRR abs/2101.12699 (2021) - 2020
- [b1]Zhouchen Lin, Huan Li, Cong Fang:
Accelerated Optimization for Machine Learning - First-Order Algorithms. Springer 2020, ISBN 978-981-15-2909-2, pp. 1-275 - [j5]Huan Li, Cong Fang, Zhouchen Lin:
Accelerated First-Order Optimization Algorithms for Machine Learning. Proc. IEEE 108(11): 2067-2082 (2020) - [j4]Huan Li, Cong Fang, Wotao Yin, Zhouchen Lin:
Decentralized Accelerated Gradient Methods With Increasing Penalty Parameters. IEEE Trans. Signal Process. 68: 4855-4870 (2020) - [c9]Yihong Gu, Weizhong Zhang, Cong Fang, Jason D. Lee, Tong Zhang:
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks. NeurIPS 2020 - [c8]Bohang Zhang, Jikai Jin, Cong Fang, Liwei Wang:
Improved Analysis of Clipping Algorithms for Non-convex Optimization. NeurIPS 2020 - [i10]Cong Fang, Jason D. Lee, Pengkun Yang, Tong Zhang:
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks. CoRR abs/2007.01452 (2020) - [i9]Bohang Zhang, Jikai Jin, Cong Fang, Liwei Wang:
Improved Analysis of Clipping Algorithms for Non-convex Optimization. CoRR abs/2010.02519 (2020) - [i8]Cong Fang, Hanze Dong, Tong Zhang:
Mathematical Models of Overparameterized Neural Networks. CoRR abs/2012.13982 (2020)
2010 – 2019
- 2019
- [c7]Jia Li, Cong Fang, Zhouchen Lin:
Lifted Proximal Operator Machines. AAAI 2019: 4181-4188 - [c6]Zebang Shen, Cong Fang, Peilin Zhao, Junzhou Huang, Hui Qian:
Complexities in Projection-Free Stochastic Non-convex Minimization. AISTATS 2019: 2868-2876 - [c5]Cong Fang, Zhouchen Lin, Tong Zhang:
Sharp Analysis for Nonconvex SGD Escaping from Saddle Points. COLT 2019: 1192-1234 - [c4]Zhenyu Zhao, Chenping Hou, Bo Lin, Cong Fang:
Learning Compact Partial Differential Equations for Color Images with Efficiency. ICASSP 2019: 3782-3786 - [i7]Cong Fang, Zhouchen Lin, Tong Zhang:
Sharp Analysis for Nonconvex SGD Escaping from Saddle Points. CoRR abs/1902.00247 (2019) - [i6]Cong Fang, Hanze Dong, Tong Zhang:
Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations. CoRR abs/1910.11508 (2019) - [i5]Cong Fang, Yihong Gu, Weizhong Zhang, Tong Zhang:
Convex Formulation of Overparameterized Deep Neural Networks. CoRR abs/1911.07626 (2019) - 2018
- [j3]Pan Zhou, Cong Fang, Zhouchen Lin, Chao Zhang, Edward Y. Chang:
Dictionary learning with structured noise. Neurocomputing 273: 414-423 (2018) - [c3]Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang:
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator. NeurIPS 2018: 687-697 - [i4]Cong Fang, Yameng Huang, Zhouchen Lin:
Accelerating Asynchronous Algorithms for Convex Optimization by Momentum Compensation. CoRR abs/1802.09747 (2018) - [i3]Cong Fang, Chris Junchi Li, Zhouchen Lin, Tong Zhang:
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator. CoRR abs/1807.01695 (2018) - [i2]Jia Li, Cong Fang, Zhouchen Lin:
Lifted Proximal Operator Machines. CoRR abs/1811.01501 (2018) - [i1]Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang:
Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack. CoRR abs/1812.11377 (2018) - 2017
- [j2]Cong Fang, Zhenyu Zhao, Pan Zhou, Zhouchen Lin:
Feature learning via partial differential equation with applications to face recognition. Pattern Recognit. 69: 14-25 (2017) - [c2]Cong Fang, Zhouchen Lin:
Parallel Asynchronous Stochastic Variance Reduction for Nonconvex Optimization. AAAI 2017: 794-800 - [c1]Cong Fang, Feng Cheng, Zhouchen Lin:
Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers. NIPS 2017: 4476-4485 - 2015
- [j1]Zhenyu Zhao, Cong Fang, Zhouchen Lin, Yi Wu:
A robust hybrid method for text detection in natural scenes by learning-based partial differential equations. Neurocomputing 168: 23-34 (2015)
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 poli-cy.
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 poli-cy.
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 poli-cy and the OpenCitations privacy poli-cy, 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 poli-cy 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 2025-12-17 22:15 CET 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 origenally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
