Huishuai Zhang

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 92

Top Topics

Convex Optimization

Differentially Private

Contextual Bandit

Top Venues

Publications

Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Ruoyu Sun, Zhi-Ming Ma, Tie-Yan Liu, Zhi-Quan Luo, Wei Chen
Provable Adaptivity of Adam under Non-uniform Smoothness. KDD (2024)
Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A. Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin
Differentially Private Synthetic Data via Foundation Model APIs 2: Text. CoRR (2024)
Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
Selective Pre-training for Private Fine-tuning. Trans. Mach. Learn. Res. 2024 (2024)
Chao Zhou, Huishuai Zhang, Jiang Bian, Weiming Zhang, Nenghai Yu
\copyright Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model. CoRR (2024)
Zhuocheng Gong, Ang Lv, Jian Guan, Junxi Yan, Wei Wu, Huishuai Zhang, Minlie Huang, Dongyan Zhao, Rui Yan
Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules. CoRR (2024)
Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao, Yikang Shen
Efficient Continual Pre-training by Mitigating the Stability Gap. CoRR (2024)
Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. CoRR (2024)
Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, Sung Ju Hwang
Automatic Jailbreaking of the Text-to-Image Generative AI Systems. CoRR (2024)
Bohan Wang, Huishuai Zhang, Qi Meng, Ruoyu Sun, Zhi-Ming Ma, Wei Chen
On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond. CoRR (2024)
Zihao Jiang, Yunkai Dang, Dong Pang, Huishuai Zhang, Weiran Huang
FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models? CoRR (2023)
Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian
UADB: Unsupervised Anomaly Detection Booster. ICDE (2023)
Bohan Wang, Huishuai Zhang, Zhiming Ma, Wei Chen
Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions. COLT (2023)
Bohan Wang, Huishuai Zhang, Zhi-Ming Ma, Wei Chen
Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions. CoRR (2023)
Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang
Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent. Trans. Mach. Learn. Res. 2023 (2023)
Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
On the Generalization Properties of Diffusion Models. NeurIPS (2023)
Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen
Closing the gap between the upper bound and lower bound of Adam's iteration complexity. NeurIPS (2023)
Kun Song, Huimin Ma, Bochao Zou, Huishuai Zhang, Weiran Huang
FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning. NeurIPS (2023)
Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
On the Generalization Properties of Diffusion Models. CoRR (2023)
Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen
Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity. CoRR (2023)
Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
Selective Pre-training for Private Fine-tuning. CoRR (2023)
Prin Phunyaphibarn, Junghyun Lee, Bohan Wang, Huishuai Zhang, Chulhee Yun
Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study. CoRR (2023)
Kaipeng Zheng, Huishuai Zhang, Weiran Huang
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation. CoRR (2023)
Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He
Denoising Masked Autoencoders Help Robust Classification. ICLR (2023)
Kaipeng Zheng, Huishuai Zhang, Weiran Huang
DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation. NeurIPS (2023)
Kun Song, Huimin Ma, Bochao Zou, Huishuai Zhang, Weiran Huang
FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning. CoRR (2023)
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping. ICLR (2023)
Huishuai Zhang, Da Yu, Yiping Lu, Di He
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks. AISTATS (2023)
Junyao Gao, Xinyang Jiang, Huishuai Zhang, Yifan Yang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao
Similarity Distribution Based Membership Inference Attack on Person Re-identification. AAAI (2023)
Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian
UADB: Unsupervised Anomaly Detection Booster. CoRR (2023)
Shufang Xie, Huishuai Zhang, Junliang Guo, Xu Tan, Jiang Bian, Hany Hassan Awadalla, Arul Menezes, Tao Qin, Rui Yan
ResiDual: Transformer with Dual Residual Connections. CoRR (2023)
Kai Qiu, Huishuai Zhang, Zhirong Wu, Stephen Lin
Exploring Transferability for Randomized Smoothing. CoRR (2023)
Jingwen Fu, Bohan Wang, Huishuai Zhang, Zhizheng Zhang, Wei Chen, Nanning Zheng
When and Why Momentum Accelerates SGD: An Empirical Study. CoRR (2023)
Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang
Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent. CoRR (2022)
Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu
Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization. CoRR (2022)
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
Differentially Private Fine-tuning of Language Models. ICLR (2022)
Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart. CVPR (2022)
Junyao Gao, Xinyang Jiang, Huishuai Zhang, Yifan Yang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao
Similarity Distribution based Membership Inference Attack on Person Re-identification. CoRR (2022)
Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum. ICML (2022)
Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping. CoRR (2022)
Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Zhi-Ming Ma, Tie-Yan Liu, Wei Chen
Provable Adaptivity in Adam. CoRR (2022)
Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He
Denoising Masked AutoEncoders are Certifiable Robust Vision Learners. CoRR (2022)
Jingwei Yi, Fangzhao Wu, Huishuai Zhang, Bin Zhu, Tao Qi, Guangzhong Sun, Xing Xie
Robust Quantity-Aware Aggregation for Federated Learning. CoRR (2022)
Huishuai Zhang, Da Yu, Mingyang Yi, Wei Chen, Tie-Yan Liu
Stabilize deep ResNet with a sharp scaling factor τ. Mach. Learn. 111 (9) (2022)
Yi Zhou, Yingbin Liang, Huishuai Zhang
Understanding generalization error of SGD in nonconvex optimization. Mach. Learn. 111 (1) (2022)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Availability Attacks Create Shortcuts. KDD (2022)
Huishuai Zhang, Da Yu, Yiping Lu, Di He
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks. CoRR (2022)
Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS (2022)
Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma
Momentum Doesn't Change the Implicit Bias. CoRR (2021)
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning. ICLR (2021)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Indiscriminate Poisoning Attacks Are Shortcuts. CoRR (2021)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Large Scale Private Learning via Low-rank Reparametrization. ICML (2021)
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning. CoRR (2021)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Large Scale Private Learning via Low-rank Reparametrization. CoRR (2021)
Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
Adversarial Training with Rectified Rejection. CoRR (2021)
Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD. NeurIPS (2021)
Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A. Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
Differentially Private Fine-tuning of Language Models. CoRR (2021)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
How Does Data Augmentation Affect Privacy in Machine Learning? AAAI (2021)
Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD. CoRR (2021)
Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
BN-invariant sharpness regularizes the training model to better generalization. CoRR (2021)
Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu
Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit. CoRR (2021)
Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu
On Layer Normalization in the Transformer Architecture. CoRR (2020)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary. CoRR (2020)
Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia. CoRR (2020)
Shicong Cen, Huishuai Zhang, Yuejie Chi, Wei Chen, Tie-Yan Liu
Convergence of Distributed Stochastic Variance Reduced Methods Without Sampling Extra Data. IEEE Trans. Signal Process. 68 (2020)
Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu
On Layer Normalization in the Transformer Architecture. ICML (2020)
Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
Gradient Perturbation is Underrated for Differentially Private Convex Optimization. IJCAI (2020)
Jerry Li, Aaron Sidford, Kevin Tian, Huishuai Zhang
Well-Conditioned Methods for Ill-Conditioned Systems: Linear Regression with Semi-Random Noise. CoRR (2020)
Huishuai Zhang, Da Yu, Wei Chen, Tie-Yan Liu
Training Over-parameterized Deep ResNet Is almost as Easy as Training a Two-layer Network. CoRR (2019)
Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu, Jian Yin
Gradient Perturbation is Underrated for Differentially Private Convex Optimization. CoRR (2019)
Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh
SGD Converges to Global Minimum in Deep Learning via Star-convex Path. CoRR (2019)
Qi Meng, Shuxin Zheng, Huishuai Zhang, Wei Chen, Qiwei Ye, Zhi-Ming Ma, Nenghai Yu, Tie-Yan Liu
G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space. ICLR (Poster) (2019)
Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu
Capacity Control of ReLU Neural Networks by Basis-Path Norm. AAAI (2019)
Shicong Cen, Huishuai Zhang, Yuejie Chi, Wei Chen, Tie-Yan Liu
Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data. CoRR (2019)
Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
BN-invariant Sharpness Regularizes the Training Model to Better Generalization. IJCAI (2019)
Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh
SGD Converges to Global Minimum in Deep Learning via Star-convex Path. ICLR (Poster) (2019)
Huishuai Zhang, Yuejie Chi, Yingbin Liang
Median-Truncated Nonconvex Approach for Phase Retrieval With Outliers. IEEE Trans. Inf. Theory 64 (11) (2018)
Yi Zhou, Yingbin Liang, Huishuai Zhang
Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization. CoRR (2018)
Huishuai Zhang, Wei Chen, Tie-Yan Liu
On the Local Hessian in Back-propagation. NeurIPS (2018)
Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu
Capacity Control of ReLU Neural Networks by Basis-path Norm. CoRR (2018)
Huishuai Zhang, Wei Chen, Tie-Yan Liu
Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation. CoRR (2018)
Huishuai Zhang, Yingbin Liang, Lifeng Lai, Shlomo Shamai Shitz
Multi-Key Generation Over a Cellular Model With a Helper. IEEE Trans. Inf. Theory 63 (6) (2017)
Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher
Block-diagonal Hessian-free Optimization for Training Neural Networks. CoRR (2017)
Huishuai Zhang, Yingbin Liang, Yuejie Chi
A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms. J. Mach. Learn. Res. 18 (2017)
Yuanxin Li, Yuejie Chi, Huishuai Zhang, Yingbin Liang
Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent. CoRR (2017)
Huishuai Zhang, Yingbin Liang
Reshaped Wirtinger Flow for Solving Quadratic System of Equations. NIPS (2016)
Huishuai Zhang, Yuejie Chi, Yingbin Liang
Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow. ICML (2016)
Huishuai Zhang, Yingbin Liang
Reshaped Wirtinger Flow for Solving Quadratic Systems of Equations. CoRR (2016)
Yi Zhou, Huishuai Zhang, Yingbin Liang
Geometrical properties and accelerated gradient solvers of non-convex phase retrieval. Allerton (2016)
Yi Zhou, Huishuai Zhang, Yingbin Liang
On Compressive orthonormal Sensing. Allerton (2016)
Huishuai Zhang, Yi Zhou, Yingbin Liang
Analysis of Robust PCA via Local Incoherence. NIPS (2015)
Huishuai Zhang, Yingbin Liang, Lifeng Lai, Shlomo Shamai
Two-key generation for a cellular model with a helper. ISIT (2015)
Huishuai Zhang, Yingbin Liang, Lifeng Lai
Secret key capacity: Talk or keep silent? ISIT (2015)
Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang
The Capacity Region of the Source-Type Model for Secret Key and Private Key Generation. IEEE Trans. Inf. Theory 60 (10) (2014)
Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang
The Capacity Region of the Source-Type Model for Secret Key and Private Key Generation. CoRR (2014)
Huishuai Zhang, Yingbin Liang, Lifeng Lai
Key capacity region for a cellular source model. ITW (2014)
Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang
Secret key-private key generation over three terminals: Capacity region. ISIT (2014)
Huishuai Zhang, Yingbin Liang, Lifeng Lai
Helper-assisted asymmetric two key generation. ACSSC (2014)