Huishuai Zhang

135 papers A* 32A 1B 4Misc 1Journal 86Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models. CoRR Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Yukun Li, Han Zhang, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
2026	J	`jnl`	De-Anonymization at Scale via Tournament-Style Attribution. CoRR Lirui Zhang, Huishuai Zhang
2026	J	`jnl`	FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs. CoRR Zhihan Yin, Jianxin Liang, Yueqian Wang, Yifeng Yao, Huishuai Zhang, Dongyan Zhao
2026	J	`jnl`	Learning to Generate Formally Verifiable Step-by-Step Logic Reasoning via Structured Formal Intermediaries. CoRR Luoxin Chen, Yichi Zhou, Huishuai Zhang
2026	J	`jnl`	OLion: Approaching the Hadamard Ideal by Intersecting Spectral and ℓ CoRR Zixiao Wang, Yifei Shen, Huishuai Zhang
2026	J	`jnl`	SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents. CoRR Danlong Yuan, Wei Wu, Zhengren Wang, Xueliang Zhao, Huishuai Zhang, Dongyan Zhao
2025	A*	`conf`	AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training. EMNLP Huishuai Zhang, Bohan Wang, Luoxin Chen
2025	J	`jnl`	AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training. CoRR Huishuai Zhang, Bohan Wang, Luoxin Chen
2025	J	`jnl`	Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA. CoRR Jianxin Liang, Tan Yue, Yuxuan Wang, Yueqian Wang, Zhihan Yin, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	Do LLMs "Feel"? Emotion Circuits Discovery and Control. CoRR Chenxi Wang, Yixuan Zhang, Ruiji Yu, Yufei Zheng, Lang Gao, Zirui Song, Zixiang Xu, Gus Xia, Huishuai Zhang, Dongyan Zhao, Xiuying Chen
2025	—	`conf`	Efficient Domain Continual pretraining by Mitigating the Stability Gap. ACL (1) Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	Efficient RL Training for Reasoning Models via Length-Aware Optimization. CoRR Danlong Yuan, Tian Xie, Shaohan Huang, Zhuocheng Gong, Huishuai Zhang, Chong Luo, Furu Wei, Dongyan Zhao
2025	—	`conf`	English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge. EMNLP (Findings) Zekai Zhang, Yiduo Guo, Jiuheng Lin, Shanghaoran Quan, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding. CoRR Yifeng Yao, Yike Yun, Jing Wang, Huishuai Zhang, Dongyan Zhao, Ke Tian, Zhihao Wang, Minghui Qiu, Tao Wang
2025	A*	`conf`	Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes. ICML Zhuocheng Gong, Jian Guan, Wei Wu, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes. CoRR Zhuocheng Gong, Jian Guan, Wei Wu, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning. CoRR Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models. CoRR Yueqian Wang, Xiaojun Meng, Yifan Wang, Huishuai Zhang, Dongyan Zhao
2025	—	`conf`	ReMamba: Equip Mamba with Effective Long-Sequence Modeling. EMNLP (Findings) Danlong Yuan, Jiahao Liu, Bei Li, Huishuai Zhang, Jingang Wang, Xunliang Cai, Dongyan Zhao
2025	—	`conf`	ReasVQA: Advancing VideoQA with Imperfect Reasoning Process. NAACL (Long Papers) Jianxin Liang, Xiaojun Meng, Huishuai Zhang, Yueqian Wang, Jiansheng Wei, Dongyan Zhao
2025	J	`jnl`	ReasVQA: Advancing VideoQA with Imperfect Reasoning Process. CoRR Jianxin Liang, Xiaojun Meng, Huishuai Zhang, Yueqian Wang, Jiansheng Wei, Dongyan Zhao
2025	J	`jnl`	Solving Formal Math Problems by Decomposition and Iterative Reflection. CoRR Yichi Zhou, Jianqiu Zhao, Yongxin Zhang, Bohan Wang, Siran Wang, Luoxin Chen, Jiahui Wang, Haowei Chen, Allan Jie, Xinbo Zhang, Haocheng Wang, Luong Quoc Trung, Rong Ye, Phan Nhat Hoang, Huishuai Zhang, Peng Sun, Hang Li
2025	J	`jnl`	Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries. CoRR Haoxiang Wang, Zinan Lin, Da Yu, Huishuai Zhang
2025	J	`jnl`	Synthetic Data RL: Task Definition Is All You Need. CoRR Yiduo Guo, Zhen Guo, Chuanwei Huang, Zi-Ang Wang, Zekai Zhang, Haofei Yu, Huishuai Zhang, Yikang Shen
2025	A*	`conf`	Understanding Nonlinear Implicit Bias via Region Counts in Input Space. ICML Jingwei Li, Jing Xu, Zifan Wang, Huishuai Zhang, Jingzhao Zhang
2025	J	`jnl`	Understanding Nonlinear Implicit Bias via Region Counts in Input Space. CoRR Jingwei Li, Jing Xu, Zifan Wang, Huishuai Zhang, Jingzhao Zhang
2025	A*	`conf`	Understanding Visual Detail Hallucinations of Large Vision-Language Models. IJCAI Xiaoxi Sun, Jianxin Liang, Yueqian Wang, Huishuai Zhang, Dongyan Zhao
2025	—	`conf`	VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format. EMNLP (Findings) Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao
2025	J	`jnl`	©Plug-in Authorization for Human Copyright Protection in Text-to-Image Model. Trans. Mach. Learn. Res. Chao Zhou, Huishuai Zhang, Jiang Bian, Weiming Zhang, Nenghai Yu
2024	J	`jnl`	AIDBench: A benchmark for evaluating the authorship identification capability of large language models. CoRR Zichen Wen, Dadi Guo, Huishuai Zhang
2024	J	`jnl`	Automatic Jailbreaking of the Text-to-Image Generative AI Systems. CoRR Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, Sung Ju Hwang
2024	J	`jnl`	Differentially Private Fine-tuning of Language Models. J. Priv. Confidentiality 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
2024	A*	`conf`	Differentially Private Synthetic Data via Foundation Model APIs 2: Text. ICML 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
2024	J	`jnl`	Differentially Private Synthetic Data via Foundation Model APIs 2: Text. CoRR 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
2024	J	`jnl`	Efficient Continual Pre-training by Mitigating the Stability Gap. CoRR Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao, Yikang Shen
2024	J	`jnl`	Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering. CoRR Haowei Du, Huishuai Zhang, Dongyan Zhao
2024	A*	`conf`	Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules. EMNLP Zhuocheng Gong, Ang Lv, Jian Guan, Wei Wu, Huishuai Zhang, Minlie Huang, Dongyan Zhao, Rui Yan
2024	J	`jnl`	Mixture-of-Modules: Reinventing Transformers as Dynamic Assemblies of Modules. CoRR Zhuocheng Gong, Ang Lv, Jian Guan, Junxi Yan, Wei Wu, Huishuai Zhang, Minlie Huang, Dongyan Zhao, Rui Yan
2024	J	`jnl`	On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond. CoRR Bohan Wang, Huishuai Zhang, Qi Meng, Ruoyu Sun, Zhi-Ming Ma, Wei Chen
2024	A*	`conf`	Provable Adaptivity of Adam under Non-uniform Smoothness. KDD Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Ruoyu Sun, Zhi-Ming Ma, Tie-Yan Liu, Zhi-Quan Luo, Wei Chen
2024	J	`jnl`	ReMamba: Equip Mamba with Effective Long-Sequence Modeling. CoRR Danlong Yuan, Jiahao Liu, Bei Li, Huishuai Zhang, Jingang Wang, Xunliang Cai, Dongyan Zhao
2024	J	`jnl`	Selective Pre-training for Private Fine-tuning. Trans. Mach. Learn. Res. Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
2024	J	`jnl`	Understanding Multimodal Hallucination with Parameter-Free Representation Alignment. CoRR Yueqian Wang, Jianxin Liang, Yuxuan Wang, Huishuai Zhang, Dongyan Zhao
2024	J	`jnl`	VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format. CoRR Yueqian Wang, Xiaojun Meng, Yuxuan Wang, Jianxin Liang, Jiansheng Wei, Huishuai Zhang, Dongyan Zhao
2024	J	`jnl`	\copyright Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model. CoRR Chao Zhou, Huishuai Zhang, Jiang Bian, Weiming Zhang, Nenghai Yu
2024	A*	`conf`	xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. NeurIPS Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao
2024	J	`jnl`	xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token. CoRR Xin Cheng, Xun Wang, Xingxing Zhang, Tao Ge, Si-Qing Chen, Furu Wei, Huishuai Zhang, Dongyan Zhao
2023	A	`conf`	Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks. AISTATS Huishuai Zhang, Da Yu, Yiping Lu, Di He
2023	J	`jnl`	Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity. CoRR Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen
2023	A*	`conf`	Closing the gap between the upper bound and lower bound of Adam's iteration complexity. NeurIPS Bohan Wang, Jingwen Fu, Huishuai Zhang, Nanning Zheng, Wei Chen
2023	A*	`conf`	Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions. COLT Bohan Wang, Huishuai Zhang, Zhiming Ma, Wei Chen
2023	J	`jnl`	Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions. CoRR Bohan Wang, Huishuai Zhang, Zhi-Ming Ma, Wei Chen
2023	A*	`conf`	Denoising Masked Autoencoders Help Robust Classification. ICLR Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He
2023	A*	`conf`	DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation. NeurIPS Kaipeng Zheng, Huishuai Zhang, Weiran Huang
2023	J	`jnl`	DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation. CoRR Kaipeng Zheng, Huishuai Zhang, Weiran Huang
2023	J	`jnl`	Exploring Transferability for Randomized Smoothing. CoRR Kai Qiu, Huishuai Zhang, Zhirong Wu, Stephen Lin
2023	A*	`conf`	Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping. ICLR Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
2023	A*	`conf`	FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning. NeurIPS Kun Song, Huimin Ma, Bochao Zou, Huishuai Zhang, Weiran Huang
2023	J	`jnl`	FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning. CoRR Kun Song, Huimin Ma, Bochao Zou, Huishuai Zhang, Weiran Huang
2023	J	`jnl`	FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models? CoRR Zihao Jiang, Yunkai Dang, Dong Pang, Huishuai Zhang, Weiran Huang
2023	J	`jnl`	Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent. Trans. Mach. Learn. Res. Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang
2023	J	`jnl`	Large Catapults in Momentum Gradient Descent with Warmup: An Empirical Study. CoRR Prin Phunyaphibarn, Junghyun Lee, Bohan Wang, Huishuai Zhang, Chulhee Yun
2023	A*	`conf`	On the Generalization Properties of Diffusion Models. NeurIPS Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
2023	J	`jnl`	On the Generalization Properties of Diffusion Models. CoRR Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
2023	J	`jnl`	ResiDual: Transformer with Dual Residual Connections. CoRR Shufang Xie, Huishuai Zhang, Junliang Guo, Xu Tan, Jiang Bian, Hany Hassan Awadalla, Arul Menezes, Tao Qin, Rui Yan
2023	J	`jnl`	Selective Pre-training for Private Fine-tuning. CoRR Da Yu, Sivakanth Gopi, Janardhan Kulkarni, Zinan Lin, Saurabh Naik, Tomasz Lukasz Religa, Jian Yin, Huishuai Zhang
2023	A*	`conf`	Similarity Distribution Based Membership Inference Attack on Person Re-identification. AAAI Junyao Gao, Xinyang Jiang, Huishuai Zhang, Yifan Yang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao
2023	A*	`conf`	UADB: Unsupervised Anomaly Detection Booster. ICDE Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian
2023	J	`jnl`	UADB: Unsupervised Anomaly Detection Booster. CoRR Hangting Ye, Zhining Liu, Xinyi Shen, Wei Cao, Shun Zheng, Xiaofan Gui, Huishuai Zhang, Yi Chang, Jiang Bian
2023	J	`jnl`	When and Why Momentum Accelerates SGD: An Empirical Study. CoRR Jingwen Fu, Bohan Wang, Huishuai Zhang, Zhizheng Zhang, Wei Chen, Nanning Zheng
2022	A*	`conf`	Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum. ICML Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
2022	J	`jnl`	Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks. CoRR Huishuai Zhang, Da Yu, Yiping Lu, Di He
2022	A*	`conf`	Availability Attacks Create Shortcuts. KDD Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2022	J	`jnl`	Denoising Masked AutoEncoders are Certifiable Robust Vision Learners. CoRR Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, Liwei Wang, Di He
2022	A*	`conf`	Differentially Private Fine-tuning of Language Models. ICLR 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
2022	A*	`conf`	Does Momentum Change the Implicit Regularization on Separable Data? NeurIPS Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
2022	J	`jnl`	Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping. CoRR Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, Jiang Bian
2022	J	`jnl`	Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization. CoRR Xiaodong Yang, Huishuai Zhang, Wei Chen, Tie-Yan Liu
2022	J	`jnl`	Per-Instance Privacy Accounting for Differentially Private Stochastic Gradient Descent. CoRR Da Yu, Gautam Kamath, Janardhan Kulkarni, Tie-Yan Liu, Jian Yin, Huishuai Zhang
2022	J	`jnl`	Provable Adaptivity in Adam. CoRR Bohan Wang, Yushun Zhang, Huishuai Zhang, Qi Meng, Zhi-Ming Ma, Tie-Yan Liu, Wei Chen
2022	J	`jnl`	Robust Quantity-Aware Aggregation for Federated Learning. CoRR Jingwei Yi, Fangzhao Wu, Huishuai Zhang, Bin Zhu, Tao Qi, Guangzhong Sun, Xing Xie
2022	J	`jnl`	Similarity Distribution based Membership Inference Attack on Person Re-identification. CoRR Junyao Gao, Xinyang Jiang, Huishuai Zhang, Yifan Yang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao
2022	J	`jnl`	Stabilize deep ResNet with a sharp scaling factor τ. Mach. Learn. Huishuai Zhang, Da Yu, Mingyang Yi, Wei Chen, Tie-Yan Liu
2022	A*	`conf`	Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart. CVPR Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
2022	J	`jnl`	Understanding generalization error of SGD in nonconvex optimization. Mach. Learn. Yi Zhou, Yingbin Liang, Huishuai Zhang
2021	J	`jnl`	Adversarial Training with Rectified Rejection. CoRR Tianyu Pang, Huishuai Zhang, Di He, Yinpeng Dong, Hang Su, Wei Chen, Jun Zhu, Tie-Yan Liu
2021	J	`jnl`	BN-invariant sharpness regularizes the training model to better generalization. CoRR Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
2021	J	`jnl`	Differentially Private Fine-tuning of Language Models. CoRR 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
2021	J	`jnl`	Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning. CoRR Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
2021	A*	`conf`	Do not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning. ICLR Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu
2021	A*	`conf`	How Does Data Augmentation Affect Privacy in Machine Learning? AAAI Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2021	J	`jnl`	Indiscriminate Poisoning Attacks Are Shortcuts. CoRR Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2021	A*	`conf`	Large Scale Private Learning via Low-rank Reparametrization. ICML Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2021	J	`jnl`	Large Scale Private Learning via Low-rank Reparametrization. CoRR Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2021	J	`jnl`	Momentum Doesn't Change the Implicit Bias. CoRR Bohan Wang, Qi Meng, Huishuai Zhang, Ruoyu Sun, Wei Chen, Zhi-Ming Ma
2021	A*	`conf`	Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD. NeurIPS Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
2021	J	`jnl`	Optimizing Information-theoretical Generalization Bounds via Anisotropic Noise in SGLD. CoRR Bohan Wang, Huishuai Zhang, Jieyu Zhang, Qi Meng, Wei Chen, Tie-Yan Liu
2021	J	`jnl`	Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit. CoRR Yichi Zhou, Shihong Song, Huishuai Zhang, Jun Zhu, Wei Chen, Tie-Yan Liu
2020	J	`jnl`	Adai: Separating the Effects of Adaptive Learning Rate and Momentum Inertia. CoRR Zeke Xie, Xinrui Wang, Huishuai Zhang, Issei Sato, Masashi Sugiyama
2020	J	`jnl`	Convergence of Distributed Stochastic Variance Reduced Methods Without Sampling Extra Data. IEEE Trans. Signal Process. Shicong Cen, Huishuai Zhang, Yuejie Chi, Wei Chen, Tie-Yan Liu
2020	A*	`conf`	Gradient Perturbation is Underrated for Differentially Private Convex Optimization. IJCAI Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2020	J	`jnl`	Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary. CoRR Da Yu, Huishuai Zhang, Wei Chen, Jian Yin, Tie-Yan Liu
2020	A*	`conf`	On Layer Normalization in the Transformer Architecture. ICML Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu
2020	J	`jnl`	On Layer Normalization in the Transformer Architecture. CoRR Ruibin Xiong, Yunchang Yang, Di He, Kai Zheng, Shuxin Zheng, Chen Xing, Huishuai Zhang, Yanyan Lan, Liwei Wang, Tie-Yan Liu
2020	J	`jnl`	Well-Conditioned Methods for Ill-Conditioned Systems: Linear Regression with Semi-Random Noise. CoRR Jerry Li, Aaron Sidford, Kevin Tian, Huishuai Zhang
2019	A*	`conf`	BN-invariant Sharpness Regularizes the Training Model to Better Generalization. IJCAI Mingyang Yi, Huishuai Zhang, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu
2019	A*	`conf`	Capacity Control of ReLU Neural Networks by Basis-Path Norm. AAAI Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu
2019	J	`jnl`	Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data. CoRR Shicong Cen, Huishuai Zhang, Yuejie Chi, Wei Chen, Tie-Yan Liu
2019	—	`conf`	G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space. ICLR (Poster) Qi Meng, Shuxin Zheng, Huishuai Zhang, Wei Chen, Qiwei Ye, Zhi-Ming Ma, Nenghai Yu, Tie-Yan Liu
2019	J	`jnl`	Gradient Perturbation is Underrated for Differentially Private Convex Optimization. CoRR Da Yu, Huishuai Zhang, Wei Chen, Tie-Yan Liu, Jian Yin
2019	—	`conf`	SGD Converges to Global Minimum in Deep Learning via Star-convex Path. ICLR (Poster) Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh
2019	J	`jnl`	SGD Converges to Global Minimum in Deep Learning via Star-convex Path. CoRR Yi Zhou, Junjie Yang, Huishuai Zhang, Yingbin Liang, Vahid Tarokh
2019	J	`jnl`	Training Over-parameterized Deep ResNet Is almost as Easy as Training a Two-layer Network. CoRR Huishuai Zhang, Da Yu, Wei Chen, Tie-Yan Liu
2018	J	`jnl`	Capacity Control of ReLU Neural Networks by Basis-path Norm. CoRR Shuxin Zheng, Qi Meng, Huishuai Zhang, Wei Chen, Nenghai Yu, Tie-Yan Liu
2018	J	`jnl`	Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization. CoRR Yi Zhou, Yingbin Liang, Huishuai Zhang
2018	J	`jnl`	Median-Truncated Nonconvex Approach for Phase Retrieval With Outliers. IEEE Trans. Inf. Theory Huishuai Zhang, Yuejie Chi, Yingbin Liang
2018	A*	`conf`	On the Local Hessian in Back-propagation. NeurIPS Huishuai Zhang, Wei Chen, Tie-Yan Liu
2018	J	`jnl`	Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation. CoRR Huishuai Zhang, Wei Chen, Tie-Yan Liu
2017	J	`jnl`	A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms. J. Mach. Learn. Res. Huishuai Zhang, Yingbin Liang, Yuejie Chi
2017	J	`jnl`	Block-diagonal Hessian-free Optimization for Training Neural Networks. CoRR Huishuai Zhang, Caiming Xiong, James Bradbury, Richard Socher
2017	J	`jnl`	Multi-Key Generation Over a Cellular Model With a Helper. IEEE Trans. Inf. Theory Huishuai Zhang, Yingbin Liang, Lifeng Lai, Shlomo Shamai Shitz
2017	J	`jnl`	Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent. CoRR Yuanxin Li, Yuejie Chi, Huishuai Zhang, Yingbin Liang
2016	—	`conf`	Geometrical properties and accelerated gradient solvers of non-convex phase retrieval. Allerton Yi Zhou, Huishuai Zhang, Yingbin Liang
2016	—	`conf`	On Compressive orthonormal Sensing. Allerton Yi Zhou, Huishuai Zhang, Yingbin Liang
2016	A*	`conf`	Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow. ICML Huishuai Zhang, Yuejie Chi, Yingbin Liang
2016	—	`conf`	Reshaped Wirtinger Flow for Solving Quadratic System of Equations. NIPS Huishuai Zhang, Yingbin Liang
2016	J	`jnl`	Reshaped Wirtinger Flow for Solving Quadratic Systems of Equations. CoRR Huishuai Zhang, Yingbin Liang
2015	—	`conf`	Analysis of Robust PCA via Local Incoherence. NIPS Huishuai Zhang, Yi Zhou, Yingbin Liang
2015	B	`conf`	Secret key capacity: Talk or keep silent? ISIT Huishuai Zhang, Yingbin Liang, Lifeng Lai
2015	B	`conf`	Two-key generation for a cellular model with a helper. ISIT Huishuai Zhang, Yingbin Liang, Lifeng Lai, Shlomo Shamai
2014	Misc	`conf`	Helper-assisted asymmetric two key generation. ACSSC Huishuai Zhang, Yingbin Liang, Lifeng Lai
2014	B	`conf`	Key capacity region for a cellular source model. ITW Huishuai Zhang, Yingbin Liang, Lifeng Lai
2014	B	`conf`	Secret key-private key generation over three terminals: Capacity region. ISIT Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang
2014	J	`jnl`	The Capacity Region of the Source-Type Model for Secret Key and Private Key Generation. CoRR Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang
2014	J	`jnl`	The Capacity Region of the Source-Type Model for Secret Key and Private Key Generation. IEEE Trans. Inf. Theory Huishuai Zhang, Lifeng Lai, Yingbin Liang, Hua Wang