Quanquan Gu

Publications

2025

1. Self-Play Preference Optimization for Language Model Alignment
   Yue Wu*, Zhiqing Sun*, Huizhuo Yuan*, Kaixuan Ji, Yiming Yang and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

2. Energy-Weighted Flow Matching for Offline Reinforcement Learning
   Shiyuan Zhang*, Weitong Zhang* and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025.

3. Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
   Zikun Zhang, Zixiang Chen and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

4. Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
   Heyang Zhao, Xingrui Yu, David Mark Bossens, Ivor Tsang and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025.

5. Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers
   Runjia Li, Qiwei Di and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

6. DPLM-2: A Multimodal Diffusion Protein Language Model
   Xinyou Wang, Zaixiang Zheng, Fei YE, Dongyu Xue, Shujian Huang and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

7. CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
   Yi Zhou*, Yilai Li*, Jing Yuan* and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

8. ProteinBench: A Holistic Evaluation of Protein Foundation Models
   Fei YE*, Zaixiang Zheng*, Dongyu Xue*, Yuning Shen*, Lihao Wang*, Yiming Ma, Yan Wang, Xinyou Wang, Xiangxin Zhou and Quanquan Gu, in Proc. of the 13th International Conference on Learning Representations (ICLR), Singapore, 2025. [arXiv]

2024

1. Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation
   Huizhuo Yuan*, Zixiang Chen*, Kaixuan Ji* and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

2. Achieving Constant Regret in Linear Markov Decision Processes
   Weitong Zhang*, Zhiyuan Fan*, Jiafan He and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

3. Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
   Zixiang Chen, Huizhuo Yuan, Yongqian Li, Yiwen Kou, Junkai Zhang and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

4. A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
   Heyang Zhao, Jiafan He and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

5. Matching the Statistical Query Lower Bound for k -Sparse Parity Problems with Sign Stochastic Gradient Descent
   Yiwen Kou*, Zixiang Chen*, Quanquan Gu and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

6. Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
   Xiangxin Zhou*, Dongyu Xue*, Ruizhe Chen*, Zaixiang Zheng, Liang Wang and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

7. Enhancing Large Vision Language Models with Self-Training on Image Comprehension
   Yihe Deng*, Pan Lu*, Fan Yin, Ziniu Hu, Sheng Shen, Quanquan Gu, James Zou, Kai-Wei Chang and Wei Wang, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 37, Vancouver, Canada, 2024. [arXiv]

8. Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
   Zixiang Chen*, Yihe Deng*, Huizhuo Yuan*, Kaixuan Ji and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

9. Uncertainty-Aware Reward-Free Exploration with General Function Approximation
   Junkai Zhang*, Weitong Zhang*, Dongruo Zhou and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024.

10. Feel-Good Thompson Sampling for Contextual Dueling Bandits
    Xuheng Li, Heyang Zhao and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

11. Borda Regret Minimization for Generalized Linear Dueling Bandits
    Yue Wu, Tao Jin*, Qiwei Di*, Hao Lou, Farzad Farnoud and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

12. Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption
    Chenlu Ye*, Jiafan He*, Quanquan Gu and Tong Zhang, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

13. Diffusion Language Models Are Versatile Protein Learners
    Xinyou Wang*, Zaixiang Zheng*, Fei Ye, Dongyu Xue, Shujian Huang and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

14. Protein Conformation Generation via Force-Guided SE(3) Diffusion Models
    Yan Wang*, Lihao Wang*, Yuning Shen, Yiqun Wang, Huizhuo Yuan, Yue Wu and Quanquan Gu, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

15. Position: TrustLLM: Trustworthiness in Large Language Models
    Yue Huang, Lichao Sun, ... Quanquan Gu, ... and Yue Zhao, in Proc. of the 41st International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

16. PhyGCN: Pre-trained Hypergraph Convolutional Neural Networks with Self-supervised Learning
    Yihe Deng, Ruochi Zhang, Pan Xu, Jian Ma and Quanquan Gu, Transaction of Machine Learning Research (TMLR), 2024. [arXiv]

17. On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization
    Dongruo Zhou*, Jinghui Chen*, Yuan Cao*, Ziyan Yang and Quanquan Gu, Transaction of Machine Learning Research (TMLR), 2024. [arXiv]

18. Pure Exploration in Asynchronous Federated Bandits
    Zichen Wang, Chuanhao Li, Chenyu Song, Lianghui Wang, Quanquan Gu and Huazheng Wang, in Proc. of the 40th International Conference on Uncertainty in Artificial Intelligence (UAI), Barcelona, Spain, 2024. [arXiv]

19. Benign Overfitting of Constant-Stepsize SGD for Linear Regression
    Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, Journal of Machine Learning Research (JMLR), 2023.
    The extended abstract of this paper has been published in COLT 2021.

20. How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
    Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu and Peter L. Bartlett, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. Spotlight Presentation [arXiv]

21. DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
    Xiangxin Zhou, Xiwei Cheng, Yuwei Yang, Yu Bao, Liang Wang and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024.

22. Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
    Xuheng Li, Yihe Deng, Jingfeng Wu, Dongruo Zhou and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. [arXiv]

23. Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
    Kaixuan Ji*, Qingyue Zhao*, Jiafan He, Weitong Zhang and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. [arXiv]

24. Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
    Zixiang Chen*, Yihe Deng*, Yuanzhi Li and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. [arXiv]

25. Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
    Qiwei Di, Heyang Zhao, Jiafan He and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. [arXiv]

26. Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
    Qiwei Di, Tao Jin, Yue Wu, Heyang Zhao, Farzad Farnoud and Quanquan Gu, in Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. [arXiv]

2023

1. Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
   Yiwen Kou*, Zixiang Chen* and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

2. Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
   Huizhuo Yuan*, Chris Junchi Li*, Gauthier Gidel, Michael I. Jordan, Quanquan Gu and Simon Shaolei Du, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

3. Corruption-Robust Offline Reinforcement Learning with General Function Approximation
   Chenlu Ye, Rui Yang, Quanquan Gu and Tong Zhang, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

4. Robust Learning with Progressive Data Expansion Against Spurious Correlation
   Yihe Deng*, Yu Yang*, Baharan Mirzasoleiman and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

5. Why Does Sharpness-Aware Minimization Generalize Better Than SGD?
   Zixiang Chen*, Junkai Zhang*, Yiwen Kou, Xiangning Chen, Cho-Jui Hsieh and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

6. Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency
   Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang and Quanquan Gu, in Proc. of the 36th Annual Conference on Learning Theory (COLT), Bangalore, India, 2023. [arXiv]

7. The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks
   Yuan Cao, Difan Zou, Yuanzhi Li and Quanquan Gu, in Proc. of the 36th Annual Conference on Learning Theory (COLT), Bangalore, India, 2023.

8. Efficient Privacy-Preserving Stochastic Nonconvex Optimization
   Lingxiao Wang, Bargav Jayaraman, David Evans and Quanquan Gu, in Proc. of the 39th International Conference on Uncertainty in Artificial Intelligence (UAI), Pittsburgh, PA, USA, 2023. [arXiv]

9. Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension
   Yue Wu, Jiafan He and Quanquan Gu, in Proc. of the 39th International Conference on Uncertainty in Artificial Intelligence (UAI), Pittsburgh, PA, USA, 2023. [arXiv]

10. Provably Efficient Representation Learning in Low-rank Markov Decision Processes: from online to offline RL
    Weitong Zhang*, Jiafan He*, Dongruo Zhou, Amy Zhang and Quanquan Gu, in Proc. of the 39th International Conference on Uncertainty in Artificial Intelligence (UAI), Pittsburgh, PA, USA, 2023. [arXiv]

11. Benign Overfitting in Adversarially Robust Linear Classification
    Jinghui Chen*, Yuan Cao* and Quanquan Gu, in Proc. of the 39th International Conference on Uncertainty in Artificial Intelligence (UAI), Pittsburgh, PA, USA, 2023. [arXiv]

12. Batched Neural Bandits
    Quanquan Gu**, Amin Karbasi**, Khashayar Khosravi**, Vahab Mirrokni**, Dongruo Zhou**, ACM/IMS Journal of Data Science, 2023.

13. Benign Overfitting for Two-layer ReLU Convolutional Neural Networks
    Yiwen Kou*, Zixiang Chen*, Yuanzhou Chen and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

14. Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron
    Jingfeng Wu*, Difan Zou*, Zixiang Chen*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

15. Nesterov meets optimism: Rate-optimal separable minimax optimization
    Chris Junchi Li*, Huizhuo Yuan*, Simon Du, Gauthier Gidel, Quanquan Gu and Michael I. Jordan, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

16. Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
    Yifei Min*, Jiafan He*, Tianhao Wang* and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

17. Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs
    Junkai Zhang, Weitong Zhang and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

18. Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
    Qiwei Di, Jiafan He, Dongruo Zhou and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

19. The Benefits of Mixup for Feature Learning
    Difan Zou, Yuan Cao, Yuanzhi Li and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

20. On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits
    Weitong Zhang, Jiafan He, Zhiyuan Fan and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

21. Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits
    Heyang Zhao, Dongruo Zhou, Jiafan He and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

22. Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
    Chenlu Ye, Wei Xiong, Quanquan Gu and Tong Zhang, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

23. Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
    Jiafan He, Heyang Zhao, Dongruo Zhou and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

24. Structure-informed Language Models Are Protein Designers
    Zaixiang Zheng*, Yifan Deng*, Dongyu Xue, Yi Zhou, Fei Ye and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. Oral Presentation [arXiv]

25. DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design
    Jiaqi Guan*, Xiangxin Zhou*, Yuwei Yang, Yu Bao, Jian Peng, Jianzhu Ma, Qiang Liu, Liang Wang and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

26. Personalized Federated Learning under Mixture of Distributions
    Yue Wu, Shuaicheng Zhang, Wenchao Yu, Yanchi Liu, Quanquan Gu, Dawei Zhou, Haifeng Chen and Wei Cheng in Proc. of the 40 th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

27. Multiple Models for Outbreak Decision Support in the face of Uncertainty
    Katriona Shea et al., in Proceedings of the National Academy of Sciences (PNAS), Volume 120, No. 18, 2023.

28. A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
    Zixiang Chen*, Chris Junchi Li*, Huizhuo Yuan*, Quanquan Gu and Michael I. Jordan, in Proc. of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023. Spotlight Presentation [arXiv]

29. Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization
    Difan Zou, Yuan Cao, Yuanzhi Li and Quanquan Gu, in Proc. of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023. [arXiv]

30. How Does Semi-supervised learing with Pseudo-labelers Work? A Case Study
    Yiwen Kou, Zixiang Chen, Yuan Cao and Quanquan Gu, in Proc. of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023.

31. Understanding Train-Validation Split in Meta-Learning with Neural Networks
    Xinzhe Zuo, Zixiang Chen, Huaxiu Yao, Yuan Cao and Quanquan Gu, in Proc. of the 10th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023.

2022

1. Benign Overfitting in Two-layer Convolutional Neural Networks
   Yuan Cao*, Zixiang Chen*, Mikhail Belkin and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. Oral Presentation [arXiv]

2. Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
   Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. Oral Presentation [arXiv]

3. Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
   Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

4. The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
   Jingfeng Wu*, Difan Zou*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

5. Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
   Jiafan He, Dongruo Zhou, Tong Zhang and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

6. Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium
   Chris Junchi Li*, Dongruo Zhou*, Quanquan Gu and Michael I. Jordan, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

7. A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
   Jiafan He*, Tianhao Wang*, Yifei Min*, Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

8. Towards Understanding the Mixture-of-Experts Layer in Deep Learning
   Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu and Yuanzhi Li, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

9. Active Ranking without Strong Stochastic Transitivity
   Hao Lou, Tao Jin, Yue Wu, Pan Xu, Quanquan Gu and Farzad Farnoud, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022.

10. Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes
    Chonghua Liao, Jiafan He and Quanquan Gu, in Proc. of the 14th Asia Conference on Machine Learning (ACML), Hyderabad, India, 2022.

11. Electrochemical mechanistic analysis from cyclic voltammograms based on deep learning
    Benjamin Hoar, Weitong Zhang, Shuangning Xu, Rana Deeba, Cyrille Costentin, Quanquan Gu and Chong Liu, ACS Measurement Science Au, 2022.

12. Dimension-free Complexity Bounds for High-order Nonconvex Finite-sum Optimization
    Dongruo Zhou and Quanquan Gu, in Proc. of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022.

13. Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
    Jingfeng Wu*, Difan Zou*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022. Long presentation [arXiv]

14. On the Sample Complexity of Learning Infinite-horizon Discounted Linear Kernel MDPs
    Yuanzhou Chen*, Jiafan He*, and Quanquan Gu, in Proc. of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022.

15. Learning Stochastic Shortest Path with Linear Function Approximation
    Yifei Min, Jiafan He, Tianhao Wang and Quanquan Gu, in Proc. of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022. [arXiv]

16. Neural Contextual Bandits with Deep Representation and Shallow Exploration
    Pan Xu, Zheng Wen, Handong Zhao and Quanquan Gu, in Proc. of the 10th International Conference on Learning Representations (ICLR), 2022. [arXiv]

17. On the Convergence of Certified Robust Training with Interval Bound Propagation
    Yihan Wang*, Zhouxing Shi*, Quanquan Gu and Cho-Jui Hsieh, in Proc. of the 10th International Conference on Learning Representations (ICLR), 2022.

18. Learning Neural Contextual Bandits through Perturbed Rewards
    Yiling Jia, Weitong Zhang, Dongruo Zhou, Quanquan Gu and Hongning Wang, in Proc. of the 10th International Conference on Learning Representations (ICLR), 2022.

19. Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
    Yue Wu, Dongruo Zhou and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [arXiv]

20. Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons
    Yue Wu*, Tao Jin*, Hao Lou, Pan Xu, Farzad Farnoud and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [arXiv]

21. Self-training Converts Weak Learners to Strong Learners in Mixture Models
    Spencer Frei*, Difan Zou*, Zixiang Chen* and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [arXiv]

22. Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs
    Jiafan He, Dongruo Zhou and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [arXiv]

23. Faster Perturbed Stochastic Gradient Methods for Finding Local Minima
    Zixiang Chen*, Dongruo Zhou* and Quanquan Gu, in Proc. of the 33rd International Conference on Algorithmic Learning Theory (ALT), Paris, France, 2022. [arXiv]

24. Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games
    Zixiang Chen, Dongruo Zhou and Quanquan Gu, in Proc. of the 33rd International Conference on Algorithmic Learning Theory (ALT), Paris, France, 2022. [arXiv]

25. Efficient Robust Training via Backward Smoothing
    Jinghui Chen, Yu Cheng, Zhe Gan, Quanquan Gu and Jingjing Liu, in Proc. of the 36th AAAI Conference on Artificial Intelligence (AAAI), Vancouver, BC, Canada, 2022. [arXiv]

26. Evaluation of individual and ensemble probabilistic forecasts of COVID-19 mortality in the US
    Estee Y Cramer et al., in Proceedings of the National Academy of Sciences (PNAS), Volume 119, No. 15, 2022.

2021

1. The Benefits of Implicit Regularization from SGD in Least Squares Problems
   Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu, Dean P. Foster and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

2. Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures
   Yuan Cao, Quanquan Gu, Mikhail Belkin, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

3. Pure Exploration in Kernel and Neural Bandits
   Yinglun Zhu*, Dongruo Zhou*, Ruoxi Jiang*, Quanquan Gu, Rebecca Willett and Robert Nowak, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

4. Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent
   Spencer Frei and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

5. Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs
   Jiafan He, Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

6. Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation
   Jiafan He, Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

7. Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation
   Weitong Zhang, Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

8. Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints
   Tianhao Wang*, Dongruo Zhou* and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

9. Variance-Aware Off-Policy Evaluation with Linear Function Approximation
   Yifei Min*, Tianhao Wang*, Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

10. Do Wider Neural Networks Really Help Adversarial Robustness?
    Boxi Wu*, Jinghui Chen*, Deng Cai, Xiaofei He and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

11. Iterative Teacher-Aware Learning
    Luyao Yuan, Dongruo Zhou, Junhong Shen, Jingdong Gao, Jeffrey L Chen, Quanquan Gu, Ying Nian Wu and Song-Chun Zhu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

12. Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
    Hanxun Huang, Yisen Wang, Sarah Monazam Erfani, Quanquan Gu, James Bailey and Xingjun Ma, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

13. Short-term Forecasting of COVID-19 in Germany and Poland during the Second Vave–A Preregistered Study
    Johannes Bracher et al., Nature Communications, 2021. [medRxiv]

14. Benign Overfitting of Constant-Stepsize SGD for Linear Regression
    Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of the 34th Annual Conference on Learning Theory (COLT), 2021. [arXiv]

15. Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
    Dongruo Zhou, Quanquan Gu and Csaba Szepesvári, in Proc. of the 34th Annual Conference on Learning Theory (COLT), 2021. [arXiv]

16. Double Explore-then-Commit: Asymptotic Optimality and Beyond
    Tianyuan Jin, Pan Xu, Xiaokui Xiao and Quanquan Gu, in Proc. of the 34th Annual Conference on Learning Theory (COLT), 2021. [arXiv]

17. Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling
    Difan Zou, Pan Xu and Quanquan Gu, in Proc. of the 37th International Conference on Uncertainty in Artificial Intelligence (UAI), 2021. [arXiv]

18. Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
    Spencer Frei, Yuan Cao and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. Long talk [arXiv]

19. Provable Generalization of SGD-trained Neural Networks of Any Width in the Presence of Adversarial Label Noise
    Spencer Frei, Yuan Cao and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

20. Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
    Difan Zou*, Spencer Frei* and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

21. On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients
    Difan Zou and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021.

22. Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
    Dongruo Zhou, Jiafan He and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

23. Logarithmic Regret for Reinforcement Learning with Linear Function Approximation
    Jiafan He, Dongruo Zhou and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

24. MOTS: Minimax Optimal Thompson Sampling
    Tianyuan Jin, Pan Xu, Jieming Shi, Xiaokui Xiao and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

25. Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
    Tianyuan Jin, Jing Tang, Pan Xu, Keke Huang, Xiaokui Xiao and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021.

26. Towards Understanding the Spectral Bias of Deep Learning
    Yuan Cao*, Zhiying Fang*, Yue Wu*, Ding-Xuan Zhou and Quanquan Gu, in Proc. of the 30th International Joint Conference on Artificial Intelligence (IJCAI), Montreal, Canada, 2021. [arXiv]

27. Variance-reduced First-order Meta-learning for Natural Language Processing Tasks
    Lingxiao Wang, Kevin Huang, Tengyu Ma, Quanquan Gu and Jing Huang, in Proc. of 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021.

28. How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?
    Zixiang Chen*, Yuan Cao*, Difan Zou* and Quanquan Gu, in Proc. of the 9th International Conference on Learning Representations (ICLR), 2021. [arXiv]

29. Neural Thompson Sampling
    Weitong Zhang, Dongruo Zhou, Lihong Li and Quanquan Gu, in Proc. of the 9th International Conference on Learning Representations (ICLR), 2021. [arXiv]

30. Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate
    Jingfeng Wu, Difan Zou, Vladimir Braverman and Quanquan Gu, in Proc. of the 9th International Conference on Learning Representations (ICLR), 2021. [arXiv]

31. Revisiting Membership Inference Under Realistic Assumptions
    Bargav Jayaraman, Lingxiao Wang, Katherine Knipmeyer, Quanquan Gu and David Evans, 21st Privacy Enhancing Technologies Symposium (PETS), 2021. [arXiv]

2020

1. Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo
   Bao Wang*, Difan Zou*, Quanquan Gu, Stanley Osher, SIAM Journal on Scientific Computing, 2020. [arXiv]

2. A Finite Time Analysis of Two Time-Scale Actor Critic Methods
   Yue Wu, Weitong Zhang, Pan Xu and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 33, 2020. [arXiv]

3. Agnostic Learning of a Single Neuron with Gradient Descent
   Spencer Frei, Yuan Cao and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 33, 2020. [arXiv]

4. A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
   Zixiang Chen, Yuan Cao, Quanquan Gu and Tong Zhang, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 33, 2020. [arXiv]

5. Neural Contextual Bandits with UCB-Based Exploration
   Dongruo Zhou, Lihong Li and Quanquan Gu, in Proc. of the 37th International Conference on Machine Learning (ICML), 2020. [arXiv]

6. A Finite-Time Analysis of Q-Learning with Neural Network Function Approximation
   Pan Xu and Quanquan Gu, in Proc. of the 37th International Conference on Machine Learning (ICML), 2020. [arXiv]

7. Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
   Yonatan Dukler, Quanquan Gu and Guido Montufar, in Proc. of the 37th International Conference on Machine Learning (ICML), 2020. [arXiv]

8. Is Neuron Coverage a Meaningful Measure for Testing Deep Neural Networks?
   Fabrice Harel-Canada, Lingxiao Wang, Muhammad Ali Gulzar, Quanquan Gu and Miryung Kim, in Proc of ACM SIGSOFT International Symposium on the Foundations of Software Engineering (ESEC/FSE), Sacramento, California, USA, 2020.

9. RayS: A Ray Searching Method for Hard-label Adversarial Attack
   Jinghui Chen and Quanquan Gu, in Proc of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Diego, CA, USA, 2020. [arXiv]

10. Stochastic Nested Variance Reduction for Nonconvex Optimization
    Dongruo Zhou, Pan Xu and Quanquan Gu, Journal of Machine Learning Research (JMLR), 2020.
    The short version of this paper has been published in NeurIPS 2018. The journal version adds the finding local minima extension proposed in this manuscript [arXiv]

11. Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
    Jinghui Chen, Dongruo Zhou, Yiqi Tang, Ziyan Yang, Yuan Cao and Quanquan Gu, in Proc. of the 29th International Joint Conference on Artificial Intelligence (IJCAI), Yokohama, Japan , 2020. [arXiv]

12. DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
    Bao Wang, Quanquan Gu, March Boedihardjo, Lingxiao Wang, Farzin Barekat and Stanley J. Osher, In Proc of the Mathematical and Scientific Machine Learning Conference (MSML), Princeton, New Jersey, USA, 2020. [arXiv]

13. Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
    Xiao Zhang*, Jinghui Chen*, Quanquan Gu and David Evans, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Sicily, Italy, 2020. [arXiv]

14. Accelerated Factored Gradient Descent for Low-Rank Matrix Factorization
    Dongruo Zhou, Yuan Cao and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Sicily, Italy,, 2020.

15. Stochastic Recursive Variance-Reduced Cubic Regularization Methods
    Dongruo Zhou and Quanquan Gu, In Proc of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Sicily, Italy,, 2020.

    [arXiv]

16. On the Global Convergence of Training Deep Linear ResNets
    Difan Zou, Philip M. Long and Quanquan Gu, in Proc. of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020. [arXiv]

17. Sample Efficient Policy Gradient Methods with Recursive Variance Reduction
    Pan Xu, Felicia Gao and Quanquan Gu, in Proc. of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020. [arXiv]

    The short version of this paper was presented in NeurIPS 2019 Optimization Foundations of Reinforcement Learning Workshop, Vancouver, Canada.

18. Improving Neural Language Generation with Spectrum Control
    Lingxiao Wang, Jing Huang, Kevin Huang, Ziniu Hu, Guangtao Wang and Quanquan Gu, in Proc. of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020.

19. Improving Adversarial Robustness Requires Revisiting Misclassified Examples
    Yisen Wang*, Difan Zou*, Jinfeng Yi, James Bailey, Xingjun Ma and Quanquan Gu, in Proc. of the 8th International Conference on Learning Representations (ICLR), Addis Ababa, Ethiopia, 2020.

20. A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
    Jinghui Chen, Dongruo Zhou, Jinfeng Yi and Quanquan Gu, in Proc. of the 34th AAAI Conference on Artificial Intelligence (AAAI), New York, New York, USA, 2020. [arXiv]

21. Generalization Error Bounds of Gradient Descent for Learning Over-parameterized Deep ReLU Networks
    Yuan Cao and Quanquan Gu, in Proc. of the 34th AAAI Conference on Artificial Intelligence (AAAI), New York, New York, USA, 2020. [arXiv]

22. A Knowledge Transfer Framework for Differentially Private Sparse Learning
    Lingxiao Wang and Quanquan Gu, in Proc. of the 34th AAAI Conference on Artificial Intelligence (AAAI), New York, New York, USA, 2020. Oral presentation [arXiv]

23. Rank Aggregation via Heterogeneous Thurstone Preference Models
    Tao Jin*, Pan Xu*, Quanquan Gu and Farzad Farnoud, in Proc. of the 34th AAAI Conference on Artificial Intelligence (AAAI), New York, New York, USA, 2020. Oral presentation [arXiv]

2019

1. Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
   Yuan Cao and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. Spotlight presentation [arXiv]

2. An Improved Analysis of Training Over-parameterized Deep Neural Networks
   Difan Zou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. [arXiv]

3. Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks
   Spencer Frei, Yuan Cao and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. [arXiv]

4. Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks
   Yuan Cao and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. [arXiv]

5. Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
   Difan Zou*, Ziniu Hu*, Yewen Wang, Song Jiang, Yizhou Sun and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019.

6. Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction
   Difan Zou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019.

7. Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
   Difan Zou*, Yuan Cao*, Dongruo Zhou and Quanquan Gu, Machine Learning Journal (MLJ), 2019. [arXiv]

8. Stochastic Variance-Reduced Cubic Regularized Newton Methods
   Dongruo Zhou, Pan Xu and Quanquan Gu, Journal of Machine Learning Research (JMLR), 2019.
   The short version of this paper has been published in ICML 2018. The journal version adds the sample efficient extension proposed in this manuscript [arXiv]

9. An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient
   Pan Xu, Felicia Gao and Quanquan Gu, in Proc. of the 35th International Conference on Uncertainty in Artificial Intelligence (UAI), Tel Aviv, Israel, 2019. Oral presentation [arXiv]

10. Differentially Private Iterative Gradient Hard Thresholding for Sparse Learning
    Lingxiao Wang and Quanquan Gu, in Proc. of the 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao, China , 2019.

11. Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
    Dongruo Zhou and Quanquan Gu, in Proc. of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019. [arXiv]

12. On the Convergence and Robustness of Adversarial Training
    Yisen Wang, Xingjun Ma, James Bailey, Jinfeng Yi, Bowen Zhou and Quanquan Gu, in Proc. of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019. Long talk

13. Learning One-hidden-layer ReLU Networks via Gradient Descent
    Xiao Zhang*, Yaodong Yu*, Lingxiao Wang* and Quanquan Gu, In Proc of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Naha, Okinawa, Japan, 2019. [arXiv]

14. Sampling from Non-Log-Concave Distributions via Variance-Reduced Gradient Langevin Dynamics
    Difan Zou, Pan Xu and Quanquan Gu, In Proc of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), Naha, Okinawa, Japan, 2019.

2018

1. Stochastic Nested Variance Reduction for Nonconvex Optimization
   Dongruo Zhou, Pan Xu and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, Montréal, Canada, 2018. Spotlight presentation [arXiv] [Slides]

2. Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimization
   Pan Xu*, Jinghui Chen*, Difan Zou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, Montréal, Canada, 2018. Spotlight presentation [arXiv]

3. Third-order Smoothness Helps: Even Faster Stochastic Optimization Algorithms for Finding Local Minima
   Yaodong Yu*, Pan Xu* and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, Montréal, Canada, 2018. [arXiv]

4. Distributed Learning without Distress: Privacy-Preserving Empirical Risk Minimization
   Bargav Jayaraman, Lingxiao Wang, David Evans and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, Montréal, Canada, 2018.

5. Subsampled Stochastic Variance-Reduced Gradient Langevin Dynamics
   Difan Zou*, Pan Xu* and Quanquan Gu, in Proc. of the 34th International Conference on Uncertainty in Artificial Intelligence (UAI), Monterey, California, 2018.

6. Differentially Private Hypothesis Transfer Learning,
   Yang Wang, Quanquan Gu and Donald Brown, in Proc. of 28th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD’18), Dublin, Ireland, 2018.

7. Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
   Xiao Zhang*, Simon S. Du* and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018. [arXiv]

8. A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
   Xiao Zhang*, Lingxiao Wang*, Yaodong Yu and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018.

9. Stochastic Variance-Reduced Hamilton Monte Carlo Methods
   Difan Zou*, Pan Xu* and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018. [arXiv]

10. Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization
    Jinghui Chen, Pan Xu, Lingxiao Wang, Jian Ma and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018. Long talk [arXiv]

11. Continuous and Discrete-Time Accelerated Stochastic Mirror Descent for Strongly Convex Functions
    Pan Xu* and Tianhao Wang* and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018.

12. Stochastic Variance-Reduced Cubic Regularized Newton Methods
    Dongruo Zhou, Pan Xu and Quanquan Gu, in Proc. of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, 2018. [arXiv]

13. Accelerated Stochastic Mirror Descent: From Continuous-time Dynamics to Discrete-time Algorithms
    Pan Xu* and Tianhao Wang* and Quanquan Gu, in Proc of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Playa Blanca, Lanzarote, Canary Islands, 2018.

14. A Unified Framework for Nonconvex Low-Rank plus Sparse Matrix Recovery
    Xiao Zhang* and Lingxiao Wang* and Quanquan Gu, in Proc of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS), Playa Blanca, Lanzarote, Canary Islands, 2018. [arXiv]

15. Continuous-trait Probabilistic Model for Comparing Multi-species Functional Genomic Data
    Yang Yang, Quanquan Gu, Takayo Sasaki, Rachel O’neill, David Gilbert and Jian Ma, in Proc. of the 22nd Annual International Conference on Research in Computational Molecular Biology (RECOMB), 2018.

2017

1. Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization
   Pan Xu and Jian Ma and Quanquan Gu, In Proc. of Advances in Neural Information Processing Systems (NIPS) 30, Long Beach, CA, USA, 2017.

2. Fast Newton Hard Thresholding Pursuit for Sparsity Constrained Nonconvex Optimization
   Jinghui Chen and Quanquan Gu, in Proc of the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Halifax, Nova Scotia, Canada, 2017.

3. Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference
   Aditya Chaudhry, Pan Xu and Quanquan Gu, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017.

4. Variance-Reduced Stochastic Gradient High-dimensional Expectation-Maximization Algorithm
   Rongda Zhu, Lingxiao Wang, Chengxiang Zhai, Quanquan Gu, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017.

5. A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
   Lingxiao Wang* and Xiao Zhang* and Quanquan Gu, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017. Subsume this paper

6. Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
   Lingxiao Wang, Quanquan Gu, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017.

7. Communication-efficient Distributed Sparse Linear Discriminant Analysis
   Lu Tian, Quanquan Gu, in Proc of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, USA, 2017.

8. A Unified Computational and Statistical Framework for Nonconvex Low-Rank Matrix Estimation
   Lingxiao Wang* and Xiao Zhang* and Quanquan Gu, in Proc of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, USA, 2017.

9. Efficient Algorithm for Sparse Tensor-variate Gaussian Graphical Models via Gradient Descent
   Pan Xu, Tingting Zhang and Quanquan Gu, in Proc of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, USA , 2017.

10. High-dimensional Time Series Clustering via Cross-Predictability
    Dezhi Hong, Quanquan Gu and Kamin Whitehouse, in Proc of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, Florida, USA , 2017.

2016

1. Semiparametric Differential Graph Models
   Pan Xu and Quanquan Gu, In Proc. of Advances in Neural Information Processing Systems (NIPS) 29, Barcelona, Spain, 2016.

2. Identifying gene regulatory network rewiring using latent differential graphical models
   Dechao Tian and Quanquan Gu and Jian Ma, Nucleic Acids Research, 2016.

3. Accelerated Stochastic Block Coordinate Descent with Optimal Sampling
   Aston Zhang and Quanquan Gu in Proc of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA, 2016.

4. Accelerated Stochastic Block Coordinate Gradient Descent for Sparsity Constrained Nonconvex Optimization
   Jinghui Chen and Quanquan Gu, in Proc of the 32th International Conference on Uncertainty in Artificial Intelligence (UAI'16), New York / New Jersey, USA, 2016.

5. Forward Backward Greedy Algorithms for Multi-Task Learning with Faster Rates
   Lu Tian, Pan Xu and Quanquan Gu, in Proc of the 32th International Conference on Uncertainty in Artificial Intelligence (UAI'16), New York / New Jersey, USA, 2016.

6. Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation
   Huan Gui, Jiawei Han and Quanquan Gu, in Proc. of the 33th International Conference on Machine Learning (ICML), New York, USA, 2016.

7. Statistical Limits of Convex Relaxations
   Zhaoran Wang, Quanquan Gu, and Han Liu, in Proc. of the 33th International Conference on Machine Learning (ICML), New York, USA, 2016.

8. Contextual Bandits in A Collaborative Environment
   Qingyun Wu, Huazheng Wang, Quanquan Gu and Hongning Wang, The 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, Tuscany, Italy, 2016.

9. Low-Rank and Sparse Structure Pursuit via Alternating Minimization
   Quanquan Gu, Zhaoran Wang and Han Liu, in Proc of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, 2016.

   Oral presentation

10. Optimal Statistical and Computational Rates for One Bit Matrix Completion
    Renkun Ni and Quanquan Gu, in Proc of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, 2016.

11. Precision Matrix Estimation in High Dimensional Gaussian Graphical Models with Faster Rates
    Lingxiao Wang, Xiang Ren and Quanquan Gu, in Proc of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS), Cadiz, Spain, 2016.

12. Aggregating Private Sparse Learning Models Using Multi-Party Computation
    Lu Tian*, Bargav Jayaraman*, Quanquan Gu and David Evans, NIPS Workshop on Private Multi-Party Machine Learning, Cadiz, Spain, 2016.

2015

1. High Dimensional Expectation-Maximization Algorithm: Statistical Optimization and Asymptotic Normality
   Zhaoran Wang, Quanquan Gu, Yang Ning, and Han Liu, in Proc. of Advances in Neural Information Processing Systems (NIPS) 28, Montreal, Quebec, Canada, 2015.

2. Robust Classification of Information Networks by Consistent Graph Learning
   Shi Zhi, Jiawei Han, and Quanquan Gu, in Proc. of European Conf. on Machine Learning (ECML), Porto, Portugal, 2015.

3. Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing
   Rongda Zhu and Quanquan Gu, in Proc. of the 32nd International Conference on Machine Learning (ICML), Lille, France, 2015.

4. Mining drug–disease relationships as a complement to medical genetics-based drug repositioning: Where a recommendation system meets genome-wide association studies,
   Haiping Wang, Quanquan Gu, Jia Wei, Zhiwei Cao and Qi Liu, Clinical Pharmacology & Therapeutics, 451-454, 2015. (Impact Factor: 7.9)

2014

1. Sparse PCA with Oracle Property
   Quanquan Gu, Zhaoran Wang and Han Liu, In Proc. of Advances in Neural Information Processing Systems (NIPS) 27, Montreal, Quebec, Canada, 2014.

2. Robust Tensor Decomposition with Gross Corruption
   Quanquan Gu*, Huan Gui* and Jiawei Han, In Proc. of Advances in Neural Information Processing Systems (NIPS) 27, Montreal, Quebec, Canada, 2014.

3. Batch-Mode Active Learning via Error Bound Minimization
   Quanquan Gu, Tong Zhang and Jiawei Han, In Proc. of the 30th Conference on Uncertainty in Artificial Intelligence (UAI), Quebec City, Quebec, Canada, 2014.

4. Online Spectral Learning on a Graph with Bandit Feedback
   Quanquan Gu and Jiawei Han, In Proc. of the 14th IEEE International Conference on Data Mining (ICDM), Shenzhen, China, 2014.

5. A network-assisted co-clustering algorithm to discover cancer subtypes based on gene expression
   Yiyi Liu, Quanquan Gu, Jack P Hou, Jiawei Han and Jian Ma, BMC Bioinformatics, 2014.

2013

1. Selective Sampling on Graphs for Classification
   Quanquan Gu, Charu Aggarwal, Jialu Liu and Jiawei Han, In Proc. of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Chicago, USA, 2013.

2. Unsupervised Link Selection in Networks
   Quanquan Gu, Charu Aggarwal and Jiawei Han, In Proc. of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS), Scottsdale, AZ, 2013.

3. Clustered Support Vector Machines
   Quanquan Gu and Jiawei Han, In Proc. of the 16th International Conference on Artificial Intelligence and Statistics (AISTATS), Scottsdale, AZ, 2013.

2012

1. Towards Active Learning on Graphs: An Error Bound Minimization Approach
   Quanquan Gu and Jiawei Han, In Proc. of the 12th IEEE International Conference on Data Mining (ICDM), Brussels, Belgium, 2012.

2. Selective Labeling via Error Bound Minimization
   Quanquan Gu, Tong Zhang, Chris Ding and Jiawei Han, In Proc. of Advances in Neural Information Processing Systems (NIPS) 25, Lake Tahoe, Nevada, United States, 2012.

3. Locality Preserving Feature Learning
   Quanquan Gu, Marina Danilevsky, Zhenhui Li and Jiawei Han, In Proc. of the 15th International Conference on Artificial Intelligence and Statistics (AISTATS), La Palma, Canary Islands, 2012.

2011

1. Linear Discriminant Dimensionality Reduction
   Quanquan Gu, Zhenhui Li and Jiawei Han, In Proc. of the 21st European Conference on Machine Learning (ECML), Athens, Greece, 2011.

2. Generalized Fisher Score for Feature Selection
   Quanquan Gu, Zhenhui Li and Jiawei Han, In Proc. of the 27th Conference on Uncertainty in Artificial Intelligence (UAI), Barcelona, Spain, 2011.

3. Learning a Kernel for Multi-Task Clustering
   Quanquan Gu, Zhenhui Li and Jiawei Han, In Proc. of the 25th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, California, USA, 2011.

4. Joint Feature Selection and Subspace Learning
   Quanquan Gu, Zhenhui Li and Jiawei Han, In Proc. of the 22nd International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, Spain, 2011.

5. On Trivial Solution and Scale Transfer Problems in Graph Regularized NMF
   Quanquan Gu, Chris Ding and Jiawei Han, In Proc. of the 22nd International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, Spain, 2011.

2010 and Before

1. Collaborative Filtering: Weighted Nonnegative Matrix Factorization Incorporating User and Item Graphs
   Quanquan Gu, Jie Zhou and Chris Ding, In Proc. of the 10th SIAM International Conference on Data Mining (SDM), Columbus, OH, USA, 2010. [Code]

2. Learning a Shared Subspace for Multi-Task Clustering and Transductive Transfer Classification
   Quanquan Gu and Jie Zhou, In Proc. of the 9th IEEE International Conference on Data Mining (ICDM), Miami, Florida, USA, 2009. (full paper) [Code]

3. Transductive Classification via Dual Regularization
   Quanquan Gu and Jie Zhou, In Proc. of the 19th European Conference on Machine Learning (ECML), Bled, Slovenia, 2009.

4. Co-clustering on Manifolds
   Quanquan Gu and Jie Zhou, In Proc. of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Paris, France, 2009. [Code]

5. Local Learning Regularized Nonnegative Matrix Factorization
   Quanquan Gu and Jie Zhou, In Proc. of the 21st International Joint Conference on Artificial Intelligence (IJCAI), Pasadena, California, USA, 2009. [Code]

6. Local Relevance Weighted Maximum Margin Criterion for Text Classification
   Quanquan Gu and Jie Zhou, In Proc. of the 9th SIAM International Conference on Data Mining (SDM), Sparks, Nevada, USA, 2009.

Preprints

1. Local and Global Inference for High Dimensional Nonparanormal Graphical Models
   Quanquan Gu, Yuan Cao, Yang Ning, and Han Liu, arXiv:1502.02347, 2015.

2. Sharp Computational-Statistical Phase Transitions via Oracle Computational Model
   Zhaoran Wang, Quanquan Gu and Han Liu, arXiv:1512.08861, 2015.

3. Communication-efficient Distributed Estimation and Inference for Transelliptical Graphical Models
   Pan Xu and Lu Tian and Quanquan Gu, arXiv:1612.09297, 2016.

4. Robust Wirtinger Flow for Phase Retrieval with Arbitrary Corruption
   Jinghui Chen, Lingxiao Wang, Xiao Zhang and Quanquan Gu, arXiv:1704.06256, 2017.

5. Provable Multi-Objective Reinforcement Learning with Generative Models
   Dongruo Zhou, Jiahao Chen and Quanquan Gu, arXiv:2011.10134, 2020.

6. Linear Contextual Bandits with Adversarial Corruptions
   Heyang Zhao, Dongruo Zhou and Quanquan Gu, arXiv:2110.12615, 2021.

7. Adaptive Differentially Private Empirical Risk Minimization
   Xiaoxia Wu, Lingxiao Wang, Irina Cristali, Quanquan Gu and Rebecca Willett, arXiv:2110.07435, 2021.

8. Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
   Yihe Deng, Weitong Zhang, Zixiang Chen and Quanquan Gu, arXiv:2311.04205, 2023.

9. Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance
   Linxi Zhao*, Yihe Deng*, Weitong Zhang and Quanquan Gu, arXiv:2402.08680, 2024.

10. Reinforcement Learning from Human Feedback with Active Queries
    Kaixuan Ji*, Jiafan He* and Quanquan Gu, arXiv:2402.09401, 2024.

11. Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback
    Qiwei Di, Jiafan He and Quanquan Gu, arXiv:2404.10776, 2024.

12. Guided Discrete Diffusion for Electronic Health Record Generation
    Jun Han*, Zixiang Chen*, Yongqian Li, Yiwen Kou, Eran Halperin, Robert E. Tillman and Quanquan Gu, arXiv:2404.12314, 2024.

Dissertation

• Online and Active Learning of Big Networks: Theory and Algorithms, Ph. D. Dissertation, University of Illinois at Urbana-Champaign, August, 2014.