Yu-Xiang Wang - RankMe

246 papers A* 68A 28B 1C 1Journal 134Unranked 13

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A second order regret bound for NormalHedge. CoRR Yoav Freund, Nicholas J. A. Harvey, Victor S. Portella, Yabing Qi, Yu-Xiang Wang
2026	J	`jnl`	ConvexBench: Can LLMs Recognize Convex Functions? CoRR Yepeng Liu, Yu Huang, Yu-Xiang Wang, Yingbin Liang, Yuheng Bu
2026	J	`jnl`	Learnable Chernoff Baselines for Inference-Time Alignment. CoRR Sunil Madhow, Yuchen Liang, Ness B. Shroff, Yingbin Liang, Yu-Xiang Wang
2026	J	`jnl`	The Inductive Bias of Convolutional Neural Networks: Locality and Weight Sharing Reshape Implicit Regularization. CoRR Tongtong Liang, Esha Singh, Rahul Parhi, Alexander Cloninger, Yu-Xiang Wang
2025	J	`jnl`	A Proximal Operator for Inducing 2:4-Sparsity. CoRR Jonas M. Kübler, Yu-Xiang Wang, Shoham Sabach, Navid Ansari, Matthäus Kleindessner, Kailash Budhathoki, Volkan Cevher, George Karypis
2025	J	`jnl`	A Proximal Operator for Inducing 2:4-Sparsity. Trans. Mach. Learn. Res. Jonas M. Kübler, Yu-Xiang Wang, Shoham Sabach, Navid Ansari, Matthäus Kleindessner, Kailash Budhathoki, Volkan Cevher, George Karypis
2025	A*	`conf`	AKORN: Adaptive Knots generated Online for RegressioN splines. ICML Sunil Madhow, Dheeraj Baby, Yu-Xiang Wang
2025	A*	`conf`	Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning. ICML Erchi Wang, Yuqing Zhu, Yu-Xiang Wang
2025	A*	`conf`	Adaptive Estimation and Learning under Temporal Distribution Shift. ICML Dheeraj Baby, Yifei Tang, Hieu Duy Nguyen, Yu-Xiang Wang, Rohit Pyati
2025	J	`jnl`	DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation. CoRR Shao-Yu Chu, Yuhe Tian, Yu-Xiang Wang, Haojian Jin
2025	J	`jnl`	Does Flatness imply Generalization for Logistic Loss in Univariate Two-Layer ReLU Network? CoRR Dan Qiao, Yu-Xiang Wang
2025	J	`jnl`	Generalization Below the Edge of Stability: The Role of Data Geometry. CoRR Tongtong Liang, Alexander Cloninger, Rahul Parhi, Yu-Xiang Wang
2025	—	`conf`	MoXCo: How I learned to stop exploring and love my local minima? CPAL Esha Singh, Shoham Sabach, Yu-Xiang Wang
2025	J	`jnl`	Not-a-Bandit: Provably No-Regret Drafter Selection in Speculative Decoding for LLMs. CoRR Hongyi Liu, Jiaji Huang, Zhen Jia, Youngsuk Park, Yu-Xiang Wang
2025	A*	`conf`	Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs. ICLR Xuandong Zhao, Lei Li, Yu-Xiang Wang
2025	J	`jnl`	Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private. CoRR Ruihan Wu, Erchi Wang, Zhiyuan Zhang, Yu-Xiang Wang
2025	J	`jnl`	ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs. CoRR Hongyi Liu, Rajarshi Saha, Zhen Jia, Youngsuk Park, Jiaji Huang, Shoham Sabach, Yu-Xiang Wang, George Karypis
2025	A*	`conf`	Proxsparse: Regularized Learning of Semi-Structured Sparsity masks for Pretrained LLMS. ICML Hongyi Liu, Rajarshi Saha, Zhen Jia, Youngsuk Park, Jiaji Huang, Shoham Sabach, Yu-Xiang Wang, George Karypis
2025	J	`jnl`	Purifying Approximate Differential Privacy with Randomized Post-processing. CoRR Yingyu Lin, Erchi Wang, Yi-An Ma, Yu-Xiang Wang
2025	A*	`conf`	SoK: Watermarking for AI-Generated Content. SP Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andrés Fábrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramèr, Somesh Jha, Lei Li, Yu-Xiang Wang, Dawn Song
2025	A*	`conf`	Weak-to-Strong Jailbreaking on Large Language Models. ICML Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang
2024	A*	`conf`	CPR: Retrieval Augmented Generation for Copyright Protection. CVPR Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto
2024	J	`jnl`	CPR: Retrieval Augmented Generation for Copyright Protection. CoRR Aditya Golatkar, Alessandro Achille, Luca Zancato, Yu-Xiang Wang, Ashwin Swaminathan, Stefano Soatto
2024	A*	`conf`	Communication-Efficient Federated Non-Linear Bandit Optimization. ICLR Chuanhao Li, Chong Liu, Yu-Xiang Wang
2024	A*	`conf`	Differentially Private Bias-Term Fine-tuning of Foundation Models. ICML Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2024	A*	`conf`	Differentially Private Reinforcement Learning with Self-Play. NeurIPS Dan Qiao, Yu-Xiang Wang
2024	J	`jnl`	Differentially Private Reinforcement Learning with Self-Play. CoRR Dan Qiao, Yu-Xiang Wang
2024	J	`jnl`	Efficiently Identifying Watermarked Segments in Mixed-Source Texts. CoRR Xuandong Zhao, Chenwen Liao, Yu-Xiang Wang, Lei Li
2024	—	`conf`	Improved Differentially Private Regression via Gradient Boosting. SaTML Shuai Tang, Sergül Aydöre, Michael Kearns, Saeyoung Rho, Aaron Roth, Yichen Wang, Yu-Xiang Wang, Zhiwei Steven Wu
2024	A*	`conf`	Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games. ICML Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2024	J	`jnl`	Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners. CoRR Rachel Redberg, Antti Koskela, Yu-Xiang Wang
2024	A*	`conf`	Invisible Image Watermarks Are Provably Removable Using Generative AI. NeurIPS Xuandong Zhao, Kexun Zhang, Zihao Su, Saastha Vasan, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna, Yu-Xiang Wang, Lei Li
2024	A*	`conf`	Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints. ICML Dan Qiao, Yu-Xiang Wang
2024	J	`jnl`	Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints. CoRR Dan Qiao, Yu-Xiang Wang
2024	J	`jnl`	Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning. CoRR Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
2024	A*	`conf`	Neural Collapse meets Differential Privacy: Curious behaviors of NoisyGD with Near-Perfect Representation Learning. ICML Chendi Wang, Yuqing Zhu, Weijie J. Su, Yu-Xiang Wang
2024	A*	`conf`	Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks. NeurIPS Zixuan Zhang, Kaiqi Zhang, Minshuo Chen, Yuma Takeda, Mengdi Wang, Tuo Zhao, Yu-Xiang Wang
2024	A*	`conf`	Online Feature Updates Improve Online (Generalized) Label Shift Adaptation. NeurIPS Ruihan Wu, Siddhartha Datta, Yi Su, Dheeraj Baby, Yu-Xiang Wang, Kilian Q. Weinberger
2024	J	`jnl`	Online Feature Updates Improve Online (Generalized) Label Shift Adaptation. CoRR Ruihan Wu, Siddhartha Datta, Yi Su, Dheeraj Baby, Yu-Xiang Wang, Kilian Q. Weinberger
2024	J	`jnl`	Permute-and-Flip: An optimally robust and watermarkable decoder for LLMs. CoRR Xuandong Zhao, Lei Li, Yu-Xiang Wang
2024	A*	`conf`	Pricing with Contextual Elasticity and Heteroscedastic Valuation. ICML Jianyu Xu, Yu-Xiang Wang
2024	A*	`conf`	Privacy Profiles for Private Selection. ICML Antti Koskela, Rachel Redberg, Yu-Xiang Wang
2024	J	`jnl`	Privacy Profiles for Private Selection. CoRR Antti Koskela, Rachel Redberg, Yu-Xiang Wang
2024	A*	`conf`	Provable Robust Watermarking for AI-Generated Text. ICLR Xuandong Zhao, Prabhanjan Vijendra Ananth, Lei Li, Yu-Xiang Wang
2024	J	`jnl`	SoK: Watermarking for AI-Generated Content. CoRR Xuandong Zhao, Sam Gunn, Miranda Christ, Jaiden Fairoze, Andrés Fábrega, Nicholas Carlini, Sanjam Garg, Sanghyun Hong, Milad Nasr, Florian Tramèr, Somesh Jha, Lei Li, Yu-Xiang Wang, Dawn Song
2024	A*	`conf`	Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes. NeurIPS Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang
2024	J	`jnl`	Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes. CoRR Dan Qiao, Kaiqi Zhang, Esha Singh, Daniel Soudry, Yu-Xiang Wang
2024	J	`jnl`	Toward General Function Approximation in Nonstationary Reinforcement Learning. IEEE J. Sel. Areas Inf. Theory Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2024	B	`conf`	Towards General Function Approximation in Nonstationary Reinforcement Learning. ISIT Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2024	A*	`conf`	Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy. ICLR Yingyu Lin, Yian Ma, Yu-Xiang Wang, Rachel Redberg, Zhiqi Bu
2024	—	`conf`	Watermarking for Large Language Models. ACL (5) Xuandong Zhao, Yu-Xiang Wang, Lei Li
2024	J	`jnl`	Weak-to-Strong Jailbreaking on Large Language Models. CoRR Xuandong Zhao, Xianjun Yang, Tianyu Pang, Chao Du, Lei Li, Yu-Xiang Wang, William Yang Wang
2023	J	`jnl`	"Private Prediction Strikes Back!" Private Kernelized Nearest Neighbors with Individual Renyi Filter. CoRR Yuqing Zhu, Xuandong Zhao, Chuan Guo, Yu-Xiang Wang
2023	A*	`conf`	A Privacy-Friendly Approach to Data Valuation. NeurIPS Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal
2023	A*	`conf`	Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger. NeurIPS Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2023	J	`jnl`	Challenges towards the Next Frontier in Privacy. CoRR Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
2023	J	`jnl`	Communication-Efficient Federated Non-Linear Bandit Optimization. CoRR Chuanhao Li, Chong Liu, Yu-Xiang Wang
2023	J	`jnl`	Coupling public and private gradient provably helps optimization. CoRR Ruixuan Liu, Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2023	A*	`conf`	Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive? ICLR Kaiqi Zhang, Yu-Xiang Wang
2023	A*	`conf`	Differentially Private Optimization on Large Model at Small Cost. ICML Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2023	A	`conf`	Doubly Fair Dynamic Pricing. AISTATS Jianyu Xu, Dan Qiao, Yu-Xiang Wang
2023	A	`conf`	Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy. AISTATS Rachel Redberg, Yuqing Zhu, Yu-Xiang Wang
2023	J	`jnl`	Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy. CoRR Rachel Redberg, Yuqing Zhu, Yu-Xiang Wang
2023	J	`jnl`	Generative Autoencoders as Watermark Attackers: Analyses of Vulnerabilities and Threats. CoRR Xuandong Zhao, Kexun Zhang, Yu-Xiang Wang, Lei Li
2023	A*	`conf`	Global Optimization with Parametric Function Approximation. ICML Chong Liu, Yu-Xiang Wang
2023	J	`jnl`	Improved Differentially Private Regression via Gradient Boosting. CoRR Shuai Tang, Sergül Aydöre, Michael Kearns, Saeyoung Rho, Aaron Roth, Yichen Wang, Yu-Xiang Wang, Zhiwei Steven Wu
2023	A*	`conf`	Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners. NeurIPS Rachel Redberg, Antti Koskela, Yu-Xiang Wang
2023	J	`jnl`	Logarithmic Switching Cost in Reinforcement Learning beyond Linear MDPs. CoRR Dan Qiao, Ming Yin, Yu-Xiang Wang
2023	J	`jnl`	Model-Free Algorithm with Improved Sample Efficiency for Zero-Sum Markov Games. CoRR Songtao Feng, Ming Yin, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2023	A*	`conf`	Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation. ICLR Dan Qiao, Yu-Xiang Wang
2023	A	`conf`	Near-Optimal Differentially Private Reinforcement Learning. AISTATS Dan Qiao, Yu-Xiang Wang
2023	A	`conf`	No-Regret Linear Bandits beyond Realizability. UAI Chong Liu, Ming Yin, Yu-Xiang Wang
2023	J	`jnl`	No-Regret Linear Bandits beyond Realizability. CoRR Chong Liu, Ming Yin, Yu-Xiang Wang
2023	J	`jnl`	Non-Stationary Contextual Pricing with Safety Constraints. Trans. Mach. Learn. Res. Dheeraj Baby, Jianyu Xu, Yu-Xiang Wang
2023	J	`jnl`	Non-stationary Online Learning with Memory and Non-stochastic Control. J. Mach. Learn. Res. Peng Zhao, Yu-Hu Yan, Yu-Xiang Wang, Zhi-Hua Zhou
2023	A*	`conf`	Non-stationary Reinforcement Learning under General Function Approximation. ICML Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2023	J	`jnl`	Non-stationary Reinforcement Learning under General Function Approximation. CoRR Songtao Feng, Ming Yin, Ruiquan Huang, Yu-Xiang Wang, Jing Yang, Yingbin Liang
2023	J	`jnl`	Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks. CoRR Kaiqi Zhang, Zixuan Zhang, Minshuo Chen, Mengdi Wang, Tuo Zhao, Yu-Xiang Wang
2023	J	`jnl`	Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data. CoRR Sunil Madhow, Dan Xiao, Ming Yin, Yu-Xiang Wang
2023	A*	`conf`	Offline Reinforcement Learning with Closed-Form Policy Improvement Operators. ICML Jiachen Li, Edwin Zhang, Ming Yin, Qinxun Bai, Yu-Xiang Wang, William Yang Wang
2023	A*	`conf`	Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient. ICLR Ming Yin, Mengdi Wang, Yu-Xiang Wang
2023	A*	`conf`	Offline Reinforcement Learning with Differential Privacy. NeurIPS Dan Qiao, Yu-Xiang Wang
2023	J	`jnl`	On the accuracy and efficiency of group-wise clipping in differentially private optimization. CoRR Zhiqi Bu, Ruixuan Liu, Yu-Xiang Wang, Sheng Zha, George Karypis
2023	A*	`conf`	Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms. NeurIPS Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen, Sivaraman Balakrishnan, Zachary C. Lipton, Yu-Xiang Wang
2023	J	`jnl`	Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms. CoRR Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen, Sivaraman Balakrishnan, Zachary Chase Lipton, Yu-Xiang Wang
2023	A*	`conf`	Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation. NeurIPS Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yian Ma
2023	J	`jnl`	Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation. CoRR Nikki Lijing Kuang, Ming Yin, Mengdi Wang, Yu-Xiang Wang, Yi-An Ma
2023	J	`jnl`	Pricing with Contextual Elasticity and Heteroscedastic Valuation. CoRR Jianyu Xu, Yu-Xiang Wang
2023	A	`conf`	Private Prediction Strikes Back! Private Kernelized Nearest Neighbors with Individual Rényi Filter. UAI Yuqing Zhu, Xuandong Zhao, Chuan Guo, Yu-Xiang Wang
2023	A*	`conf`	Protecting Language Generation Models via Invisible Watermarking. ICML Xuandong Zhao, Yu-Xiang Wang, Lei Li
2023	J	`jnl`	Protecting Language Generation Models via Invisible Watermarking. CoRR Xuandong Zhao, Yu-Xiang Wang, Lei Li
2023	J	`jnl`	Provable Robust Watermarking for AI-Generated Text. CoRR Xuandong Zhao, Prabhanjan Ananth, Lei Li, Yu-Xiang Wang
2023	A	`conf`	Second Order Path Variationals in Non-Stationary Online Learning. AISTATS Dheeraj Baby, Yu-Xiang Wang
2023	J	`jnl`	Smoothed Differential Privacy. Trans. Mach. Learn. Res. Ao Liu, Yu-Xiang Wang, Lirong Xia
2023	J	`jnl`	Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation. CoRR Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal
2023	J	`jnl`	Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy. CoRR Yingyu Lin, Yian Ma, Yu-Xiang Wang, Rachel Redberg
2022	A	`conf`	Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE. AISTATS Yuqing Zhu, Yu-Xiang Wang
2022	J	`jnl`	Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE. CoRR Yuqing Zhu, Yu-Xiang Wang
2022	J	`jnl`	Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger. CoRR Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2022	J	`jnl`	Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive? CoRR Kaiqi Zhang, Yu-Xiang Wang
2022	J	`jnl`	Differentially Private Bias-Term only Fine-tuning of Foundation Models. CoRR Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2022	A*	`conf`	Differentially Private Linear Sketches: Efficient Implementations and Applications. NeurIPS Fuheng Zhao, Dan Qiao, Rachel Redberg, Divyakant Agrawal, Amr El Abbadi, Yu-Xiang Wang
2022	J	`jnl`	Differentially Private Linear Sketches: Efficient Implementations and Applications. CoRR Fuheng Zhao, Dan Qiao, Rachel Redberg, Divyakant Agrawal, Amr El Abbadi, Yu-Xiang Wang
2022	J	`jnl`	Differentially Private Optimization on Large Model at Small Cost. CoRR Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
2022	—	`conf`	Distillation-Resistant Watermarking for Model Protection in NLP. EMNLP (Findings) Xuandong Zhao, Lei Li, Yu-Xiang Wang
2022	J	`jnl`	Distillation-Resistant Watermarking for Model Protection in NLP. CoRR Xuandong Zhao, Lei Li, Yu-Xiang Wang
2022	J	`jnl`	Doubly Fair Dynamic Pricing. CoRR Jianyu Xu, Dan Qiao, Yu-Xiang Wang
2022	J	`jnl`	Doubly Robust Crowdsourcing. J. Artif. Intell. Res. Chong Liu, Yu-Xiang Wang
2022	J	`jnl`	Global Optimization with Parametric Function Approximation. CoRR Chong Liu, Yu-Xiang Wang
2022	A*	`conf`	Mixed Differential Privacy in Computer Vision. CVPR Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
2022	J	`jnl`	Mixed Differential Privacy in Computer Vision. CoRR Aditya Golatkar, Alessandro Achille, Yu-Xiang Wang, Aaron Roth, Michael Kearns, Stefano Soatto
2022	J	`jnl`	Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation. CoRR Dan Qiao, Yu-Xiang Wang
2022	J	`jnl`	Near-Optimal Differentially Private Reinforcement Learning. CoRR Dan Qiao, Yu-Xiang Wang
2022	A*	`conf`	Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism. ICLR Ming Yin, Yaqi Duan, Mengdi Wang, Yu-Xiang Wang
2022	J	`jnl`	Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism. CoRR Ming Yin, Yaqi Duan, Mengdi Wang, Yu-Xiang Wang
2022	A	`conf`	Non-stationary Online Learning with Memory and Non-stochastic Control. AISTATS Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou
2022	J	`jnl`	Offline Reinforcement Learning with Closed-Form Policy Improvement Operators. CoRR Jiachen Li, Edwin Zhang, Ming Yin, Qinxun Bai, Yu-Xiang Wang, William Yang Wang
2022	J	`jnl`	Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient. CoRR Ming Yin, Mengdi Wang, Yu-Xiang Wang
2022	J	`jnl`	Offline Reinforcement Learning with Differential Privacy. CoRR Dan Qiao, Yu-Xiang Wang
2022	J	`jnl`	Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality. CoRR Ming Yin, Wenjing Chen, Mengdi Wang, Yu-Xiang Wang
2022	A	`conf`	Offline stochastic shortest path: Learning, evaluation and towards optimality. UAI Ming Yin, Wenjing Chen, Mengdi Wang, Yu-Xiang Wang
2022	A	`conf`	Optimal Accounting of Differential Privacy via Characteristic Function. AISTATS Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang
2022	A*	`conf`	Optimal Dynamic Regret in LQR Control. NeurIPS Dheeraj Baby, Yu-Xiang Wang
2022	J	`jnl`	Optimal Dynamic Regret in LQR Control. CoRR Dheeraj Baby, Yu-Xiang Wang
2022	A	`conf`	Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond. AISTATS Dheeraj Baby, Yu-Xiang Wang
2022	J	`jnl`	Optimal Dynamic Regret in Proper Online Learning with Strongly Convex Losses and Beyond. CoRR Dheeraj Baby, Yu-Xiang Wang
2022	—	`conf`	Provably Confidential Language Modelling. NAACL-HLT Xuandong Zhao, Lei Li, Yu-Xiang Wang
2022	J	`jnl`	Provably Confidential Language Modelling. CoRR Xuandong Zhao, Lei Li, Yu-Xiang Wang
2022	A*	`conf`	Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost. ICML Dan Qiao, Ming Yin, Ming Min, Yu-Xiang Wang
2022	J	`jnl`	Sample-Efficient Reinforcement Learning with loglog(T) Switching Cost. CoRR Dan Qiao, Ming Yin, Ming Min, Yu-Xiang Wang
2022	J	`jnl`	Second Order Path Variationals in Non-Stationary Online Learning. CoRR Dheeraj Baby, Yu-Xiang Wang
2022	A*	`conf`	SeqPATE: Differentially Private Text Generation via Knowledge Distillation. NeurIPS Zhiliang Tian, Yingxiu Zhao, Ziyue Huang, Yu-Xiang Wang, Nevin L. Zhang, He He
2022	A	`conf`	Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise. AISTATS Jianyu Xu, Yu-Xiang Wang
2022	J	`jnl`	Towards Agnostic Feature-based Dynamic Pricing: Linear Policies vs Linear Valuation with Unknown Noise. CoRR Jianyu Xu, Yu-Xiang Wang
2022	J	`jnl`	Towards Differential Relational Privacy and its use in Question Answering. CoRR Simone Bombari, Alessandro Achille, Zijian Wang, Yu-Xiang Wang, Yusheng Xie, Kunwar Yashraj Singh, Srikar Appalaraju, Vijay Mahadevan, Stefano Soatto
2022	J	`jnl`	Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks. CoRR Kaiqi Zhang, Ming Yin, Yu-Xiang Wang
2021	A	`conf`	An Optimal Reduction of TV-Denoising to Adaptive Online Learning. AISTATS Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang
2021	J	`jnl`	An Optimal Reduction of TV-Denoising to Adaptive Online Learning. CoRR Dheeraj Baby, Xuandong Zhao, Yu-Xiang Wang
2021	A	`conf`	Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability. EuroS&P Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, Giovanni Vigna
2021	A	`conf`	Inter-Series Attention Model for COVID-19 Forecasting. SDM Xiaoyong Jin, Yu-Xiang Wang, Xifeng Yan
2021	A*	`conf`	Logarithmic Regret in Feature-based Dynamic Pricing. NeurIPS Jianyu Xu, Yu-Xiang Wang
2021	J	`jnl`	Logarithmic Regret in Feature-based Dynamic Pricing. CoRR Jianyu Xu, Yu-Xiang Wang
2021	J	`jnl`	Multivariate Trend Filtering for Lattice Data. CoRR Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Addison J. Hu, Ryan J. Tibshirani
2021	A*	`conf`	Near-Optimal Offline Reinforcement Learning via Double Variance Reduction. NeurIPS Ming Yin, Yu Bai, Yu-Xiang Wang
2021	J	`jnl`	Near-Optimal Offline Reinforcement Learning via Double Variance Reduction. CoRR Ming Yin, Yu Bai, Yu-Xiang Wang
2021	A	`conf`	Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning. AISTATS Ming Yin, Yu Bai, Yu-Xiang Wang
2021	J	`jnl`	Non-stationary Online Learning with Memory and Non-stochastic Control. CoRR Peng Zhao, Yu-Xiang Wang, Zhi-Hua Zhou
2021	J	`jnl`	Optimal Accounting of Differential Privacy via Characteristic Function. CoRR Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang
2021	A*	`conf`	Optimal Dynamic Regret in Exp-Concave Online Learning. COLT Dheeraj Baby, Yu-Xiang Wang
2021	J	`jnl`	Optimal Dynamic Regret in Exp-Concave Online Learning. CoRR Dheeraj Baby, Yu-Xiang Wang
2021	A*	`conf`	Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings. NeurIPS Ming Yin, Yu-Xiang Wang
2021	J	`jnl`	Optimal Uniform OPE and Model-based Offline Reinforcement Learning in Time-Homogeneous, Reward-Free and Task-Agnostic Settings. CoRR Ming Yin, Yu-Xiang Wang
2021	A*	`conf`	Privately Publishable Per-instance Privacy. NeurIPS Rachel Redberg, Yu-Xiang Wang
2021	J	`jnl`	Privately Publishable Per-instance Privacy. CoRR Rachel Redberg, Yu-Xiang Wang
2021	A	`conf`	Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning. AISTATS Chong Liu, Yuqing Zhu, Kamalika Chaudhuri, Yu-Xiang Wang
2021	J	`jnl`	Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning. J. Mach. Learn. Res. Chong Liu, Yuqing Zhu, Kamalika Chaudhuri, Yu-Xiang Wang
2021	A*	`conf`	Towards Instance-Optimal Offline Reinforcement Learning with Pessimism. NeurIPS Ming Yin, Yu-Xiang Wang
2021	J	`jnl`	Towards Instance-Optimal Offline Reinforcement Learning with Pessimism. CoRR Ming Yin, Yu-Xiang Wang
2020	A*	`conf`	Adaptive Online Estimation of Piecewise Polynomial Trends. NeurIPS Dheeraj Baby, Yu-Xiang Wang
2020	J	`jnl`	Adaptive Online Estimation of Piecewise Polynomial Trends. CoRR Dheeraj Baby, Yu-Xiang Wang
2020	A*	`conf`	An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm. ICML Chris Decarolis, Mukul Ram, Seyed Esmaeili, Yu-Xiang Wang, Furong Huang
2020	A	`conf`	Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning. AISTATS Ming Yin, Yu-Xiang Wang
2020	J	`jnl`	Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning. CoRR Ming Yin, Yu-Xiang Wang
2020	J	`jnl`	Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferability. CoRR Hojjat Aghakhani, Dongyu Meng, Yu-Xiang Wang, Christopher Kruegel, Giovanni Vigna
2020	A*	`conf`	Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift. NeurIPS Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoffrey J. Gordon
2020	J	`jnl`	Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift. CoRR Remi Tachet des Combes, Han Zhao, Yu-Xiang Wang, Geoffrey J. Gordon
2020	A*	`conf`	Improving Sparse Vector Technique with Renyi Differential Privacy. NeurIPS Yuqing Zhu, Yu-Xiang Wang
2020	J	`jnl`	Inter-Series Attention Model for COVID-19 Forecasting. CoRR Xiaoyong Jin, Yu-Xiang Wang, Xifeng Yan
2020	J	`jnl`	Near Optimal Provable Uniform Convergence in Off-Policy Evaluation for Reinforcement Learning. CoRR Ming Yin, Yu Bai, Yu-Xiang Wang
2020	J	`jnl`	Patch-Based Image Hallucination for Super Resolution With Detail Reconstruction From Similar Sample Images. IEEE Trans. Multim. Chieh-Chi Kao, Yu-Xiang Wang, Jonathan Waltman, Pradeep Sen
2020	A*	`conf`	Private-kNN: Practical Differential Privacy for Computer Vision. CVPR Yuqing Zhu, Xiang Yu, Manmohan Chandraker, Yu-Xiang Wang
2020	J	`jnl`	Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning. CoRR Chong Liu, Yuqing Zhu, Kamalika Chaudhuri, Yu-Xiang Wang
2020	J	`jnl`	Subsampled Rényi Differential Privacy and Analytical Moments Accountant. J. Priv. Confidentiality Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan
2020	J	`jnl`	Voting-based Approaches For Differentially Private Federated Learning. CoRR Yuqing Zhu, Xiang Yu, Yi-Hsuan Tsai, Francesco Pittaluga, Masoud Faraki, Manmohan Chandraker, Yu-Xiang Wang
2019	A	`conf`	A Higher-Order Kolmogorov-Smirnov Test. AISTATS Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas, Ryan J. Tibshirani
2019	J	`jnl`	A Higher-Order Kolmogorov-Smirnov Test. CoRR Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas, Ryan J. Tibshirani
2019	J	`jnl`	A Theoretical Analysis of Noisy Sparse Subspace Clustering on Dimensionality-Reduced Data. IEEE Trans. Inf. Theory Yining Wang, Yu-Xiang Wang, Aarti Singh
2019	J	`jnl`	Doubly Robust Crowdsourcing. CoRR Chong Liu, Yu-Xiang Wang
2019	A*	`conf`	Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. NeurIPS Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, Xifeng Yan
2019	J	`jnl`	Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting. CoRR Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang, Xifeng Yan
2019	A	`conf`	Imitation-Regularized Offline Learning. AISTATS Yifei Ma, Yu-Xiang Wang, Balakrishnan Narayanaswamy
2019	J	`jnl`	Imitation-Regularized Offline Learning. CoRR Yifei Ma, Yu-Xiang Wang, Balakrishnan Narayanaswamy
2019	A*	`conf`	Online Forecasting of Total-Variation-bounded Sequences. NeurIPS Dheeraj Baby, Yu-Xiang Wang
2019	J	`jnl`	Online Forecasting of Total-Variation-bounded Sequences. CoRR Dheeraj Baby, Yu-Xiang Wang
2019	J	`jnl`	Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling. CoRR Tengyang Xie, Yifei Ma, Yu-Xiang Wang
2019	J	`jnl`	Per-instance Differential Privacy. J. Priv. Confidentiality Yu-Xiang Wang
2019	A*	`conf`	Poission Subsampled Rényi Differential Privacy. ICML Yuqing Zhu, Yu-Xiang Wang
2019	J	`jnl`	Provable Subspace Clustering: When LRR Meets SSC. IEEE Trans. Inf. Theory Yu-Xiang Wang, Huan Xu, Chenlei Leng
2019	A*	`conf`	Provably Efficient Q-Learning with Low Switching Cost. NeurIPS Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang
2019	J	`jnl`	Provably Efficient Q-Learning with Low Switching Cost. CoRR Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang
2019	—	`conf`	ProxQuant: Quantized Neural Networks via Proximal Operators. ICLR (Poster) Yu Bai, Yu-Xiang Wang, Edo Liberty
2019	A	`conf`	Subsampled Renyi Differential Privacy and Analytical Moments Accountant. AISTATS Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan
2019	J	`jnl`	Technical Note - Nonstationary Stochastic Optimization Under Oper. Res. Xi Chen, Yining Wang, Yu-Xiang Wang
2019	A*	`conf`	Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling. NeurIPS Tengyang Xie, Yifei Ma, Yu-Xiang Wang
2018	—	`conf`	Compression by the signs: distributed learning is a two-way street. ICLR (Workshop) Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
2018	A*	`conf`	Detecting and Correcting for Label Shift with Black Box Predictors. ICML Zachary C. Lipton, Yu-Xiang Wang, Alexander J. Smola
2018	J	`jnl`	Detecting and Correcting for Label Shift with Black Box Predictors. CoRR Zachary C. Lipton, Yu-Xiang Wang, Alexander J. Smola
2018	A*	`conf`	Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising. ICML Borja Balle, Yu-Xiang Wang
2018	J	`jnl`	Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising. CoRR Borja Balle, Yu-Xiang Wang
2018	J	`jnl`	Patch-Based Image Hallucination for Super Resolution with Detail Reconstruction from Similar Sample Images. CoRR Chieh-Chi Kao, Yu-Xiang Wang, Jonathan Waltman, Pradeep Sen
2018	J	`jnl`	ProxQuant: Quantized Neural Networks via Proximal Operators. CoRR Yu Bai, Yu-Xiang Wang, Edo Liberty
2018	A	`conf`	Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain. UAI Yu-Xiang Wang
2018	J	`jnl`	Revisiting differentially private linear regression: optimal and adaptive prediction & estimation in unbounded domain. CoRR Yu-Xiang Wang
2018	A*	`conf`	SIGNSGD: Compressed Optimisation for Non-Convex Problems. ICML Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Animashree Anandkumar
2018	J	`jnl`	Subsampled Rényi Differential Privacy and Analytical Moments Accountant. CoRR Yu-Xiang Wang, Borja Balle, Shiva Prasad Kasiviswanathan
2018	J	`jnl`	signSGD: compressed optimisation for non-convex problems. CoRR Jeremy Bernstein, Yu-Xiang Wang, Kamyar Azizzadenesheli, Anima Anandkumar
2017	A	`conf`	Attributing Hacks. AISTATS Ziqi Liu, Alexander J. Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng
2017	—	`conf`	Higher-Order Total Variation Classes on Grids: Minimax Theory and Trend Filtering Methods. NIPS Veeranjaneyulu Sadhanala, Yu-Xiang Wang, James Sharpnack, Ryan J. Tibshirani
2017	—	`—`	New Paradigms and Optimality Guarantees in Statistical Learning and Estimation. Yu-Xiang Wang
2017	J	`jnl`	Non-stationary Stochastic Optimization with Local Spatial and Temporal Changes. CoRR Xi Chen, Yining Wang, Yu-Xiang Wang
2017	A*	`conf`	Optimal and Adaptive Off-policy Evaluation in Contextual Bandits. ICML Yu-Xiang Wang, Alekh Agarwal, Miroslav Dudík
2017	J	`jnl`	Per-instance Differential Privacy and the Adaptivity of Posterior Sampling in Linear and Ridge regression. CoRR Yu-Xiang Wang
2016	J	`jnl`	A Minimax Theory for Adaptive Data Analysis. CoRR Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg
2016	J	`jnl`	A Theoretical Analysis of Noisy Sparse Subspace Clustering on Dimensionality-Reduced Data. CoRR Yining Wang, Yu-Xiang Wang, Aarti Singh
2016	J	`jnl`	Attributing Hacks. CoRR Ziqi Liu, Alexander J. Smola, Kyle Soska, Yu-Xiang Wang, Qinghua Zheng
2016	A	`conf`	DiFacto: Distributed Factorization Machines. WSDM Mu Li, Ziqi Liu, Alexander J. Smola, Yu-Xiang Wang
2016	A	`conf`	Graph Connectivity in Noisy Sparse Subspace Clustering. AISTATS Yining Wang, Yu-Xiang Wang, Aarti Singh
2016	A	`conf`	Graph Sparsification Approaches for Laplacian Smoothing. AISTATS Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Ryan J. Tibshirani
2016	J	`jnl`	Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle. J. Mach. Learn. Res. Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg
2016	J	`jnl`	Noisy Sparse Subspace Clustering. J. Mach. Learn. Res. Yu-Xiang Wang, Huan Xu
2016	C	`conf`	On-Average KL-Privacy and Its Equivalence to Generalization for Max-Entropy Mechanisms. PSD Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg
2016	J	`jnl`	On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms. CoRR Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg
2016	J	`jnl`	Optimal and Adaptive Off-policy Evaluation in Contextual Bandits. CoRR Yu-Xiang Wang, Alekh Agarwal, Miroslav Dudík
2016	A*	`conf`	Parallel and Distributed Block-Coordinate Frank-Wolfe Algorithms. ICML Yu-Xiang Wang, Veeranjaneyulu Sadhanala, Wei Dai, Willie Neiswanger, Suvrit Sra, Eric P. Xing
2016	—	`conf`	Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers. NIPS Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Ryan J. Tibshirani
2016	J	`jnl`	Trend Filtering on Graphs. J. Mach. Learn. Res. Yu-Xiang Wang, James Sharpnack, Alexander J. Smola, Ryan J. Tibshirani
2015	A*	`conf`	A Deterministic Analysis of Noisy Sparse Subspace Clustering for Dimensionality-reduced Data. ICML Yining Wang, Yu-Xiang Wang, Aarti Singh
2015	J	`jnl`	Clustering Consistent Sparse Subspace Clustering. CoRR Yining Wang, Yu-Xiang Wang, Aarti Singh
2015	—	`conf`	Differentially private subspace clustering. NIPS Yining Wang, Yu-Xiang Wang, Aarti Singh
2015	A	`conf`	Fast Differentially Private Matrix Factorization. RecSys Ziqi Liu, Yu-Xiang Wang, Alexander J. Smola
2015	J	`jnl`	Fast Differentially Private Matrix Factorization. CoRR Ziqi Liu, Yu-Xiang Wang, Alexander J. Smola
2015	J	`jnl`	Learning with Differential Privacy: Stability, Learnability and the Sufficiency and Necessity of ERM Principle. CoRR Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg
2015	J	`jnl`	Practical Matrix Completion and Corruption Recovery Using Proximal Alternating Robust Subspace Minimization. Int. J. Comput. Vis. Yu-Xiang Wang, Choon Meng Lee, Loong-Fah Cheong, Kim-Chuan Toh
2015	A*	`conf`	Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo. ICML Yu-Xiang Wang, Stephen E. Fienberg, Alexander J. Smola
2015	J	`jnl`	Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo. CoRR Yu-Xiang Wang, Stephen E. Fienberg, Alexander J. Smola
2015	A	`conf`	Trend Filtering on Graphs. AISTATS Yu-Xiang Wang, James Sharpnack, Alexander J. Smola, Ryan J. Tibshirani
2015	A*	`conf`	Who Supported Obama in 2012?: Ecological Inference through Distribution Regression. KDD Seth R. Flaxman, Yu-Xiang Wang, Alexander J. Smola
2014	J	`jnl`	Block-Sparse RPCA for Salient Motion Detection. IEEE Trans. Pattern Anal. Mach. Intell. Zhi Gao, Loong-Fah Cheong, Yu-Xiang Wang
2014	A*	`conf`	The Falling Factorial Basis and Its Statistical Applications. ICML Yu-Xiang Wang, Alexander J. Smola, Ryan J. Tibshirani
2014	J	`jnl`	Trend Filtering on Graphs. CoRR Yu-Xiang Wang, James Sharpnack, Alexander J. Smola, Ryan J. Tibshirani
2013	—	`conf`	Noisy Sparse Subspace Clustering. ICML (1) Yu-Xiang Wang, Huan Xu
2013	J	`jnl`	Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization. CoRR Yu-Xiang Wang, Choon Meng Lee, Loong-Fah Cheong, Kim-Chuan Toh
2013	—	`conf`	Provable Subspace Clustering: When LRR meets SSC. NIPS Yu-Xiang Wang, Huan Xu, Chenlei Leng
2012	J	`jnl`	Stability of matrix factorization for collaborative filtering CoRR Yu-Xiang Wang, Huan Xu
2012	A*	`conf`	Stability of matrix factorization for collaborative filtering. ICML Yu-Xiang Wang, Huan Xu
2011	—	`conf`	Real-Time Volume Caustics with Image-Based Photon Tracing. CAD/Graphics Yu-Xiang Wang, Bin Wang, Li Chen