default search action
Hongyang Zhang 0001
Person information
- affiliation: University of Waterloo, David R. Cheriton School of Computer Science, Canada
- affiliation (former): Toyota Technological Institute at Chicago, USA
- affiliation (PhD 2019): Carnegie Mellon University, School of Computer Science, Machine Learning Department, Pittsburgh, PA, USA
- affiliation (former): Peking University, School of Electronics Engineering and Computer Science, MOE, Key Laboratory of Machine Perception, Beijing, China
Other persons with the same name
- Hongyang Zhang — disambiguation page
- Hongyang Zhang 0002
— Xidian University, Xi'an, School of Aerospace Science and Technology, China
- Hongyang Zhang 0003
- Hongyang Zhang 0004 — Beijing Normal University, College of Information Science and Technology, China
- Hongyang R. Zhang (aka: Hongyang Ryan Zhang, Hongyang Zhang 0005) — Northeastern University, Boston, MA, USA (and 2 more)
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
- [j9]Lang Huang
Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning. IEEE Trans. Pattern Anal. Mach. Intell. 46(3): 1362-1377 (2024) - [c39]Yimu Wang, Yihan Wu, Hongyang Zhang:
Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains. AAAI 2024: 15689-15697 - [c38]Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang:
EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. EMNLP 2024: 7421-7432 - [c37]Zhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, Heng Huang:
Unbiased Watermark for Large Language Models. ICLR 2024 - [c36]Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang:
RAIN: Your Language Models Can Align Themselves without Finetuning. ICLR 2024 - [c35]Yu Du, Fangyun Wei, Hongyang Zhang:
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls. ICML 2024 - [c34]Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang:
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. ICML 2024 - [c33]Yihan Wu, Zhengmian Hu, Junfeng Guo, Hongyang Zhang, Heng Huang:
A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models. ICML 2024 - [c32]Yuhui Li, Zejia Wu, Chao Zhang, Hongyang Zhang:
Direct-Effect Risk Minimization for Domain Generalization. ECML/PKDD (3) 2024: 39-57 - [i45]Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang:
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty. CoRR abs/2401.15077 (2024) - [i44]Yu Du, Fangyun Wei, Hongyang Zhang:
AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls. CoRR abs/2402.04253 (2024) - [i43]Haochen Sun, Jason Li, Hongyang Zhang:
zkLLM: Zero Knowledge Proofs for Large Language Models. CoRR abs/2404.16109 (2024) - [i42]Yihan Wu, Ruibo Chen, Zhengmian Hu, Yanshuo Chen, Junfeng Guo, Hongyang Zhang, Heng Huang:
Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions. CoRR abs/2406.02603 (2024) - [i41]Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang:
EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees. CoRR abs/2406.16858 (2024) - 2023
- [j8]Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang:
An Analysis of Robustness of Non-Lipschitz Networks. J. Mach. Learn. Res. 24: 98:1-98:43 (2023) - [j7]Zhuangfei Hu
Recovery From Non-Decomposable Distance Oracles. IEEE Trans. Inf. Theory 69(10): 6443-6469 (2023) - [c31]Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang:
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games. AISTATS 2023: 9607-9636 - [c30]Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang:
Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets. CVPR 2023: 20564-20574 - [c29]Xinyi Wang, Michael Saxon
Causal Balancing for Domain Generalization. ICLR 2023 - [c28]Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao:
Understanding the Impact of Adversarial Robustness on Accuracy Disparity. ICML 2023: 13679-13709 - [c27]Yihan Wu, Heng Huang, Hongyang Zhang:
A Law of Robustness beyond Isoperimetry. ICML 2023: 37439-37455 - [c26]Zhuangfei Hu, Xinda Li, David P. Woodruff, Hongyang Zhang, Shufan Zhang
Recovery from Non-Decomposable Distance Oracles. ITCS 2023: 73:1-73:22 - [c25]Fangcheng Liu, Chao Zhang, Hongyang Zhang:
Towards Transferable Unrestricted Adversarial Examples with Minimum Changes. SaTML 2023: 327-338 - [i40]Yimu Wang, Dinghuai Zhang, Yihan Wu, Heng Huang, Hongyang Zhang:
Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets. CoRR abs/2306.15482 (2023) - [i39]Yimu Wang, Peng Shi, Hongyang Zhang:
Investigating the Existence of "Secret Language" in Language Models. CoRR abs/2307.12507 (2023) - [i38]Haochen Sun, Hongyang Zhang:
zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training. CoRR abs/2307.16273 (2023) - [i37]Yuhui Li, Fangyun Wei, Jinjing Zhao, Chao Zhang, Hongyang Zhang:
RAIN: Your Language Models Can Align Themselves without Finetuning. CoRR abs/2309.07124 (2023) - [i36]Yihan Wu, Zhengmian Hu, Hongyang Zhang, Heng Huang:
DiPmark: A Stealthy, Efficient and Resilient Watermark for Large Language Models. CoRR abs/2310.07710 (2023) - [i35]Zhengmian Hu, Lichang Chen, Xidong Wu, Yihan Wu, Hongyang Zhang, Heng Huang:
Unbiased Watermark for Large Language Models. CoRR abs/2310.10669 (2023) - [i34]Haochen Sun, Hongyang Zhang:
zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training. IACR Cryptol. ePrint Arch. 2023: 1174 (2023) - 2022
- [c24]Minghan Li
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking. EMNLP 2022: 333-345 - [c23]Yihan Wu, Hongyang Zhang, Heng Huang:
RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval. ICML 2022: 24266-24279 - [c22]Dinghuai Zhang, Hongyang Zhang, Aaron C. Courville, Yoshua Bengio, Pradeep Ravikumar, Arun Sai Suggala:
Building Robust Ensembles via Margin Boosting. ICML 2022: 26669-26692 - [c21]Avrim Blum, Omar Montasser, Greg Shakhnarovich, Hongyang Zhang:
Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness. NeurIPS 2022 - [i33]Fangcheng Liu, Chao Zhang, Hongyang Zhang:
Towards Transferable Unrestricted Adversarial Examples with Minimum Changes. CoRR abs/2201.01102 (2022) - [i32]Avrim Blum, Omar Montasser, Greg Shakhnarovich, Hongyang Zhang:
Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness. CoRR abs/2202.05920 (2022) - [i31]Hongyang Zhang, Yihan Wu, Heng Huang:
How Many Data Are Needed for Robust Learning? CoRR abs/2202.11592 (2022) - [i30]Minghan Li, Xinyu Zhang, Ji Xin, Hongyang Zhang, Jimmy Lin:
Certified Error Control of Candidate Set Pruning for Two-Stage Relevance Ranking. CoRR abs/2205.09638 (2022) - [i29]Dinghuai Zhang, Hongyang Zhang, Aaron C. Courville, Yoshua Bengio, Pradeep Ravikumar, Arun Sai Suggala:
Building Robust Ensembles via Margin Boosting. CoRR abs/2206.03362 (2022) - [i28]Xinyi Wang, Michael Saxon, Jiachen Li, Hongyang Zhang, Kun Zhang, William Yang Wang:
Causal Balancing for Domain Generalization. CoRR abs/2206.05263 (2022) - [i27]Yihan Wu, Hongyang Zhang, Heng Huang:
RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval. CoRR abs/2206.11225 (2022) - [i26]Zhuangfei Hu, Xinda Li, David P. Woodruff, Hongyang Zhang, Shufan Zhang
Recovery from Non-Decomposable Distance Oracles. CoRR abs/2209.05676 (2022) - [i25]Luke Rowe, Benjamin Thérien, Krzysztof Czarnecki, Hongyang Zhang:
A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition. CoRR abs/2210.02577 (2022) - [i24]Maria-Florina Balcan, Rattana Pukdee, Pradeep Ravikumar, Hongyang Zhang:
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games. CoRR abs/2210.12606 (2022) - [i23]Yihan Wu, Xinda Li, Florian Kerschbaum, Heng Huang, Hongyang Zhang:
Towards Robust Dataset Learning. CoRR abs/2211.10752 (2022) - [i22]Yuhui Li, Zejia Wu, Chao Zhang, Hongyang Zhang:
Direct-Effect Risk Minimization for Domain Generalization. CoRR abs/2211.14594 (2022) - [i21]Yuzheng Hu, Fan Wu, Hongyang Zhang, Han Zhao:
Understanding the Impact of Adversarial Robustness on Accuracy Disparity. CoRR abs/2211.15762 (2022) - 2021
- [c20]Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao:
Adversarial Robustness of Stabilized Neural ODE Might be from Obfuscated Gradients. MSML 2021: 497-515 - [i20]Lang Huang, Chao Zhang, Hongyang Zhang:
Self-Adaptive Training: Bridging the Supervised and Self-Supervised Learning. CoRR abs/2101.08732 (2021) - [i19]Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Wenzhao Xiang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Wenzhao Xiang, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang:
Unrestricted Adversarial Attacks on ImageNet Competition. CoRR abs/2110.09903 (2021) - 2020
- [j6]Avrim Blum, Travis Dick, Naren Manoj, Hongyang Zhang:
Random Smoothing Might be Unable to Certify L∞ Robustness for High-Dimensional Images. J. Mach. Learn. Res. 21: 211:1-211:21 (2020) - [c19]Xiao Yang, Fangyun Wei, Hongyang Zhang, Jun Zhu:
Design and Interpretation of Universal Adversarial Patches in Face Detection. ECCV (17) 2020: 174-191 - [c18]Lang Huang, Chao Zhang, Hongyang Zhang:
Self-Adaptive Training: beyond Empirical Risk Minimization. NeurIPS 2020 - [c17]Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov, Kamalika Chaudhuri:
A Closer Look at Accuracy vs. Robustness. NeurIPS 2020 - [i18]Avrim Blum, Travis Dick, Naren Manoj
Random Smoothing Might be Unable to Certify 𝓁∞ Robustness for High-Dimensional Images. CoRR abs/2002.03517 (2020) - [i17]Lang Huang, Chao Zhang, Hongyang Zhang:
Self-Adaptive Training: beyond Empirical Risk Minimization. CoRR abs/2002.10319 (2020) - [i16]Yao-Yuan Yang, Cyrus Rashtchian, Hongyang Zhang, Ruslan Salakhutdinov, Kamalika Chaudhuri:
Adversarial Robustness Through Local Lipschitzness. CoRR abs/2003.02460 (2020) - [i15]Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao:
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients. CoRR abs/2009.13145 (2020) - [i14]Maria-Florina Balcan, Avrim Blum, Dravyansh Sharma, Hongyang Zhang:
On the Power of Abstention and Data-Driven Decision Making for Adversarial Robustness. CoRR abs/2010.06154 (2020)
2010 – 2019
- 2019
- [b1]Hongyang Zhang:
New Advances in Sparse Learning, Deep Networks, and Adversarial Learning: Theory and Applications. Carnegie Mellon University, USA, 2019 - [j5]Maria-Florina Balcan, Yingyu Liang, Zhao Song, David P. Woodruff, Hongyang Zhang:
Non-Convex Matrix Completion and Related Problems via Strong Duality. J. Mach. Learn. Res. 20: 102:1-102:56 (2019) - [c16]Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov:
Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex. AISTATS 2019: 1099-1109 - [c15]Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan:
Theoretically Principled Trade-off between Robustness and Accuracy. ICML 2019: 7472-7482 - [c14]Zhao Song, Ruosong Wang, Lin F. Yang
Efficient Symmetric Norm Regression via Linear Sketching. NeurIPS 2019: 828-838 - [c13]Chen Dan, Hong Wang, Hongyang Zhang, Yuchen Zhou, Pradeep Ravikumar:
Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation. NeurIPS 2019: 2537-2548 - [c12]Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang:
Testing Matrix Rank, Optimally. SODA 2019: 727-746 - [i13]Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, Michael I. Jordan:
Theoretically Principled Trade-off between Robustness and Accuracy. CoRR abs/1901.08573 (2019) - [i12]Zhao Song, Ruosong Wang, Lin F. Yang, Hongyang Zhang, Peilin Zhong:
Efficient Symmetric Norm Regression via Linear Sketching. CoRR abs/1910.01788 (2019) - [i11]Chen Dan, Hong Wang, Hongyang Zhang, Yuchen Zhou, Pradeep Ravikumar:
Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation. CoRR abs/1910.13618 (2019) - [i10]Xiao Yang, Fangyun Wei, Hongyang Zhang, Xiang Ming, Jun Zhu:
Design and Interpretation of Universal Adversarial Patches in Face Detection. CoRR abs/1912.05021 (2019) - 2018
- [j4]Thierry Bouwmans
On the Applications of Robust PCA in Image and Video Processing. Proc. IEEE 106(8): 1427-1457 (2018) - [c11]Vasileios Nakos, Xiaofei Shi
Improved Algorithms for Adaptive Compressed Sensing. ICALP 2018: 90:1-90:14 - [c10]Maria-Florina Balcan, Yingyu Liang, David P. Woodruff, Hongyang Zhang:
Matrix Completion and Related Problems via Strong Duality. ITCS 2018: 5:1-5:22 - [i9]Vasileios Nakos, Xiaofei Shi, David P. Woodruff, Hongyang Zhang:
Improved Algorithms for Adaptive Compressed Sensing. CoRR abs/1804.09673 (2018) - [i8]Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov:
Deep Neural Networks with Multi-Branch Architectures Are Less Non-Convex. CoRR abs/1806.01845 (2018) - [i7]Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang:
Testing Matrix Rank, Optimally. CoRR abs/1810.08171 (2018) - [i6]Hongyang Zhang, Susu Xu, Jiantao Jiao, Pengtao Xie, Ruslan Salakhutdinov, Eric P. Xing:
Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-Generator Architectures. CoRR abs/1811.08010 (2018) - 2017
- [c9]Hongyang Zhang, Shan You, Zhouchen Lin, Chao Xu:
Fast Compressive Phase Retrieval under Bounded Noise. AAAI 2017: 2884-2890 - [c8]Maria-Florina Balcan, Travis Dick, Yingyu Liang, Wenlong Mou, Hongyang Zhang:
Differentially Private Clustering in High-Dimensional Euclidean Spaces. ICML 2017: 322-331 - [c7]Yichong Xu, Hongyang Zhang, Aarti Singh, Artur Dubrawski, Kyle Miller:
Noise-Tolerant Interactive Learning Using Pairwise Comparisons. NIPS 2017: 2431-2440 - [c6]Maria-Florina Balcan, Hongyang Zhang:
Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions. NIPS 2017: 4796-4805 - [i5]Maria-Florina Balcan, Hongyang Zhang:
S-Concave Distributions: Towards Broader Distributions for Noise-Tolerant and Sample-Efficient Learning Algorithms. CoRR abs/1703.07758 (2017) - [i4]Maria-Florina Balcan, Yingyu Liang, David P. Woodruff, Hongyang Zhang:
Optimal Sample Complexity for Matrix Completion and Related Problems via 𝓁s2-Regularization. CoRR abs/1704.08683 (2017) - 2016
- [j3]Hongyang Zhang, Zhouchen Lin, Chao Zhang:
Completing Low-Rank Matrices With Corrupted Samples From Few Coefficients in General Basis. IEEE Trans. Inf. Theory 62(8): 4748-4768 (2016) - [c5]Pranjal Awasthi, Maria-Florina Balcan, Nika Haghtalab, Hongyang Zhang:
Learning and 1-bit Compressed Sensing under Asymmetric Noise. COLT 2016: 152-192 - [c4]Maria-Florina Balcan, Hongyang Zhang:
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling. NIPS 2016: 2955-2963 - [i3]Maria-Florina Balcan, Hongyang Zhang:
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling. CoRR abs/1612.00100 (2016) - 2015
- [j2]Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao
Relations Among Some Low-Rank Subspace Recovery Models. Neural Comput. 27(9): 1915-1950 (2015) - [c3]Hongyang Zhang, Zhouchen Lin, Chao Zhang, Edward Y. Chang:
Exact Recoverability of Robust PCA via Outlier Pursuit with Tight Recovery Bounds. AAAI 2015: 3143-3149 - [c2]Xin Shi, Chao Zhang, Fangyun Wei, Hongyang Zhang, Yiyuan She:
Manifold-Regularized Selectable Factor Extraction for Semi-supervised Image Classification. BMVC 2015: 132.1-132.11 - [i2]Hongyang Zhang, Zhouchen Lin, Chao Zhang:
Completing Low-Rank Matrices with Corrupted Samples from Few Coefficients in General Basis. CoRR abs/1506.07615 (2015) - 2014
- [j1]Hongyang Zhang
Robust latent low rank representation for subspace clustering. Neurocomputing 145: 369-373 (2014) - [i1]Hongyang Zhang, Zhouchen Lin, Chao Zhang, Junbin Gao:
Relations among Some Low Rank Subspace Recovery Models. CoRR abs/1412.2196 (2014) - 2013
- [c1]Hongyang Zhang, Zhouchen Lin, Chao Zhang:
A Counterexample for the Validity of Using Nuclear Norm as a Convex Surrogate of Rank. ECML/PKDD (2) 2013: 226-241
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 2024-11-19 20:49 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 originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: