Publications: (by dates, by topics)

Survey

1. [Survey] Approximation Algorithms for Stochastic Combinatorial Optimization Problems. Jian Li and Yu Liu. Journal of the Operations Research Society of China. (invited survey paper, excellent paper award),2016 [paper] [ Show Abstract ]

Stochastic optimization has established itself as a major method to handle uncertainty in various optimization problems, by modeling the uncertainty by a probability distribution over possible realizations. Traditionally, the main focus in stochastic optimization has been various stochastic mathematical programming (such as linear programming, convex programming). In recent years, there has been a surge of interest in stochastic combinatorial optimization problems from the theoretical computer science community. In this article, we survey some of the recent results on various stochastic versions of classical combinatorial optimization problems. Since most problems in this domain are NP-hard (or \#P-hard, or even PSPACE-hard), we focus on the results which provide polynomial time approximation algorithms, with provable approximation guarantees. Our discussions are centered around a few representative problems, such as stochastic knapsack, stochastic matching, multi-armed bandit etc. We use these examples to introduce several popular stochastic models, such as the fixed set model, 2-stage stochastic optimization model, stochastic adaptive probing model etc, as well as some useful techniques for designing approximation algorithms for stochastic combinatorial optimization problems, including the linear programming relaxation approach, boosted sampling, content resolution schemes, Poisson approximation etc. We also provide some open research questions along the way. Our purpose is to provide the readers a quick glimpse to the models, problems and techniques in this area, and hopefully inspire new contributions.

Selected Papers full list in google scholar page

1. AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally. Shaowen Wang, Yuke Zheng, Tansheng Zhu, Shuang Chen, Shaofan Liu, Suncong Zheng, Jian Li. The 43th International Conference on Machine Learning (ICML 2026). [Openreview] [Techloop Article] [ Show Abstract ]

2. Navigating the Alpha Jungle: an LLM-Powered MCTS Framework for Formulaic Factor Mining. Yu Shi, Yitong Duan, Jian Li. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026 Oral) [ArXiv] [CSDN Article] [ Show Abstract ]

3. Capacitated Center Problems with Two-Sided Bounds and Outliers, Hu Ding, Lunjia Hu, Huang Lingxiao and Jian Li. Workshop on Algorithms and Data Structures (WADS 2017) [ArXiv][ Show Abstract ]

4. Learning Arbitrary Statistical Mixtures of Discrete Distributions. Jian Li, Yuval Rabani, Leonard J. Schulman, Chaitanya Swamy, In ACM Symposium on the Theory of Computing (STOC 2015). [ArXiv] [ Show Abstract ]

5. Gradient Descent Maximizes the Margin of Homogeneous Neural Networks. Kaifeng Lyu, Jian Li. 2020 International Conference on Learning Representations (ICLR2020, Oral) [ArXiv] [ Show Abstract ]

6. Nearly Instance Optimal Sample Complexity Bounds for Top-k Arm Selection. Lijie Chen, Jian Li, Mingda Qiao. The 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017). [full version in ArXiv] [ Show Abstract ]

7. Kronos: A Foundation Model for the Language of Financial Markets. Yu Shi, Zongliang Fu, Shuo Chen, Bohan Zhao, Wei Xu, Changshui Zhang, Jian Li. The 40th Annual AAAI Conference on Artificial Intelligence (AAAI 2026) [ArXiv] [Github] [Zhihu Article] [ Show Abstract ]

8. Range Queries on Uncertain Data, Jian Li, Haitao Wang International Symposium on Algorithms and Computation (ISAAC 2014). Journal version accepted in TCS, 2015 [arXiv]. [ Show Abstract ]

9. K-Means Clustering with Distributed Dimension. Hu Ding, Yu Liu, Lingxiao Huang, Jian Li. The 33rd International Conference on Machine Learning (ICML 2016). [Paper] [Supplementary] [ Show Abstract ]

10. Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability. Zhouzi Li, Zixuan Wang, Jian Li. Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2022). [ArXiv] [ Show Abstract ]

11. Stochastic k-Center and j-Flat-Center Problems. Lingxiao Huang, Jian Li. ACM-SIAM Symposium on Discrete Algorithms (SODA17). [ArXiv] [ Show Abstract ]

12. Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior. Tongda Xu, Jian Li, Xinjie Zhang, Xingtong Ge, Dailan He, Xiyan Cai, Ming Sun, Yan Wang, Jingjing Liu, Ya-Qin Zhang The 9th International Conference on Learning Representations (ICLR 2025) [Paper] [ Show Abstract ]

13. Sensitivity Analysis and Explanations for Robust Query Evaluation in Probabilistic Databases. Bhargav Kanagal, Jian Li, Amol Deshpande. In Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD 2011), Athens, Greece, 2011. [Paper] [ Show Abstract ]

14. OpenFE++: Efficient Automated Feature Generation via Feature Interaction. Lei Wang, Yu Shi, Yifei Jin, Jian Li. SIAM International Conference on Data Mining (SDM25). [ArXiv] [ Show Abstract ]

15. A Simple Proximal Stochastic Gradient Method for Nonsmooth Nonconvex Optimization. Zhize Li, Jian Li. Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018 spotlight) [ArXiv] [ Show Abstract ]

16. Energy Efficient Scheduling via Partial Shutdown. Samir Khuller, Jian Li, Barna Saha. In the ACM-SIAM Symposium on Discrete Algorithms (SODA 2010), Austin, USA, 2010. [Paper] [ Show Abstract ]

17. Data Generation using Declarative Constraints. Arvind Arasu, Raghav Kaushik, and Jian Li. In Proceedings of the ACM SIGMOD International Conference on Management of Data (SIGMOD 2011), Athens, Greece, 2011. [Paper] [ Show Abstract ]

18. GLIME: General, Stable and Local LIME Explanation. Zeren Tan, Tian Yang, Jian Li. Thirty-seventh Conference on Neural Information Processing Systems. 2023 (NeurIPS 2023, spotlight) [paper] [ Show Abstract ]

19. Maximizing Expected Utility for Stochastic Combinatorial Optimization Problems; Jian Li, and Amol Deshpande; Mathematics of Operations Research (MOR), Vol. 44, No. 1, 2018. Conference version in Proceedings of the 52nd Annual IEEE Symposium on Foundations of Computer Science (FOCS 2011), Palm Springs, California, 2011. [Paper] [ArXiv]. [ Show Abstract ]

20. MacMic: Executing Iceberg Orders via Hierarchical Reinforcement Learning Hui Niu, Siyuan Li, Jian Li. The 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024). [Paper] [ Show Abstract ]

21. epsilon-Kernel Coresets for Stochastic Points. Lingxiao Huang, Jian Li, Jeff Phillips and Haitao Wang. The 24rd Annual European Symposium on Algorithms (ESA 2016). [ArXiv] [ Show Abstract ]

22. Near-Linear Time Approximation Schemes for Geometric Maximum Coverage, Kai Jin, Jian Li, Haitao Wang, Bowei Zhang, Ningye Zhang. Theoretical Computer Science (TCS 2018). [conference version] [ Show Abstract ] [full version]

23. On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs. Wei Cao, Jian Li, Yufei Tao, Zhize Li. Neural Information Processing Systems (NIPS), 2015. [full paper] [ Show Abstract ]

24. Towards Generalizable Reinforcement Learning for Trade Execution. Chuheng Zhang, Yitong Duan, Xiaoyu Chen, Jianyu Chen, Jian Li, Li Zhao. The 32th International Joint Conference on Artificial Intelligence (IJCAI 2023) [Paper] [ Show Abstract ]

25. A Constant Factor Approximation Algorithm for Fault-Tolerant k-Median. Mohammadtaghi Hajiaghayi, Wei Hu, Jian Li, Shi Li, Barna Saha. In the ACM-SIAM Symposium on Discrete Algorithms(SODA 2014), Portland, Oregon, USA. Journal version in ACM Transcations on Algorithms, 2016. [ArXiv] [ Show Abstract ]

26. Adaptivity Gaps for Stochastic Probing with Subadditive Functions. Jian Li, Yinchen Liu, Yiran Zhang. The 66th Annual Symposium on Foundations of Computer Science (FOCS 2025). [ArXiv] [ Show Abstract ]

27. Stochastic Online Greedy Learning with Semi-bandit Feedbacks. Tian Lin, Jian Li, Wei Chen. Neural Information Processing Systems (NIPS), 2015. [full paper] [ Show Abstract ]

28. On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning. Jian Li, Xuanyuan Luo, Mingda Qiao. 2020 International Conference on Learning Representations (ICLR2020) [ArXiv] [ Show Abstract ]

29. CDB: optimizing queries with crowd-based selections and joins. Guolinag Li, Chengliang Chai, Ju Fan, Jian Li, Yudian Zheng etc. 2017 ACM International Conference on Management of Data (SIGMOD 2017). [paper][ Show Abstract ]

30. Gradient Boosting With Piece-Wise Linear Regression Trees. Yu Shi, Jian Li, Zhize Li. The 28th International Joint Conference on Artificial Intelligence (IJCAI 2019). [ArXiv] [ Show Abstract ]

31. When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks. Dong Wang, Junbo Zhang, Wei Cao, Jian Li, Yu Zheng. The Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018) [Paper] [Code and Data] [ Show Abstract ]

32. Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation. Jin Xu, Xiaojiang Liu, Jianhao Yan, Deng Cai, Huayang Li, Jian Li. Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2022). [ArXiv] [ Show Abstract ]

33. A PTAS for the Weighted Unit Disk Cover Problem, Jian Li, Yifei Jin. The 42nd International Colloquium on Automata, Languages, and Programming (ICALP 2015) [ArXiv] [ Show Abstract ]

34. LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition. Jin Xu, Xu Tan, Yi Ren, Tao Qin, Jian Li, Sheng Zhao, and Tie-Yan Liu. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2020). [Paper] [ Show Abstract ]

35. eps-Coresets for Clustering (with Outliers) in Doubling Metrics. Lingxiao Huang, Shaofeng H.-C. Jiang, Jian Li, Xuan Wu. The 59th Annual IEEE Symposium on Foundations of Computer Science (FOCS 2018) [Full version in ArXiv] [ Show Abstract ]

36. Consensus Answers for Queries over Probabilistic Databases. Jian Li and Amol Deshpande. In the 28th ACM Symposium on Principles of Database Systems (PODS 2009). Providence, USA, 2009 [Paper][slides] [ Show Abstract ]

37. k-Regret Minimizing Set: Efficient Algorithms and Hardness. Wei Cao, Jian Li, Haitao Wang, Kangning Wang, Ruosong Wang, Raymond Chi-Wing Wong and Wei Zhan. The 20th International Conference on Database Theory (ICDT 2017), Venice, Italy. (best newcomer award) [paper] [full version] [ Show Abstract ]

38. Cost-Effective Crowdsourced Entity Resolution: A Partial-Order Approach, Chengliang Chai, Guoliang Li, Jian Li, Dong Deng, Jianhua Feng. The annual ACM SIGMOD conference 2016. Journal version in VLDB Journal 2018. [Paper] [ Show Abstract ][Journal link]

39. A PTAS for a Class of Stochastic Dynamic Programs. Hao Fu, Jian Li and Pan Xu. The 45th International Colloquium on Automata, Languages, and Programming (ICALP 2018) [ArXiv] [ Show Abstract ]

40. Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization. Jing Zhou, Zongyu Lin, Yanan Zheng, Jian Li, Zhilin Yang. The Eleventh International Conference on Learning Representations (ICLR 2023 spotlight). [Paper] [ Show Abstract ]

41. Trinary-Projection Trees for Approximate Nearest Neighbor Search. Jingdong Wang, Naiyan Wang, You Jia; Jian Li, Gang Zeng, Hongbin Zha, Xian-Sheng Hua. The IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2013 [Paper]

42. FeatureLTE: Learning to Estimate Feature Importance . Tianping Zhang, Zhaoyang Wang, Chen Qian, Jian Li, Yin Lou. Proceedings of the ACM on Management of Data (SIGMOD 2024). [Paper] [ Show Abstract ]

43. Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws. Zhixuan Pan, Shaowen Wang, Pengfei Liao, Jian Li. Proceedings of the Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS 2025, spotlight). [ArXiv] [Zhihu Article][Slides] [ Show Abstract ]

44. OpenFE: Automated Feature Generation with Expert-level Performance. Tianping Zhang, Zheyu Zhang, Zhiyuan Fan, Haoyan Luo, Fengyuan Liu, Qian Liu, Wei Cao, Jian Li. The 40th International Conference on Machine Learning (ICML 2023) [Github] [ Show Abstract ]

45. Generalized Machine Activation Problems. Jian Li and Samir Khuller. In the ACM-SIAM Symposium on Discrete Algorithms (SODA 2011), San Francisco, USA, 2011. [Paper][slides] [ Show Abstract ]

46. Optimal PAC Multiple Arm Identification with Applications to Crowdsourcing, Yuan Zhou, Xi Chen, Jian Li. International Conference on Machine Learning. ICML 2014. [full version] [ Show Abstract ]

47. Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration. Lijie Chen, Anupam Gupta, Jian Li, Mingda Qiao, Ruosong Wang. In the 30th Annual Conference on Learning Theory (COLT 2017) [Paper] [ Show Abstract ]

48. Fully Polynomial Approximation Scheme for Approximating a Sum of Random Variables, Jian Li and Tianlin Shi. In Operation Research Letters (ORL), 2014 [ArXiv] [Code (by Tianlin)] [ Show Abstract ]

49. Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling. Liang Zeng, Lei Wang, Hui Niu, Ruchen Zhang, Ling Wang, Jian Li. The 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024). [Paper] [ Show Abstract ]

50. Towards Instance Optimal Bounds for Best Arm Identification. Lijie Chen, Jian Li, Mingda Qiao. In the 30th Annual Conference on Learning Theory (COLT 2017) [ArXiv] [ Show Abstract ]

51. On Computing Compression Trees for Data Collection in Wireless Sensor Networks. Jian Li, Amol Deshpande and Samir Khuller. In the 29th Conference on Computer Communications (INFOCOM 2010), San Diego, USA, 2010 [Paper] [slides]

52. Generalized Unrelated Machine Scheduling Problem. Shichuan Deng, Jian Li, Yuval Rabani. ACM-SIAM Symposium on Discrete Algorithms (SODA 2023). [ArXiv] [ Show Abstract ]

53. DESTPRE : A Data-Driven Approach to Destination Prediction for Taxi Rides. Mengwen Xu, Dong Wang, Jian Li. UbiComp 2016. [ Paper ] [ Show Abstract ]

54. Generalization Bounds for Gradient Methods via Discrete and Continuous Prior. Jian Li, Xuanyuan Luo. Proceedings of the Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2022). [ArXiv] [ Show Abstract ]

55. Unbiased Gradient Boosting Decision Tree with Unbiased Feature Importance. Zheyu Zhang, Tianping Zhang, Jian Li. The 32th International Joint Conference on Artificial Intelligence (IJCAI 2023) [Paper] [ Show Abstract ]

56. Efficient Algorithms for One-Dimensional k-Center Problems. Danny Z. Chen, Jian Li, Haitao Wang. Theoretical Computer Science (TCS), 2015 [ArXiv] [ Show Abstract ]

57. Egalitarian Pairwise Kidney Exchange: Fast Algorithms via Linear Programming and Parametric Flow. Jian Li, Yicheng Liu, Lingxiao Huang, Pingzhong Tang. In the 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014) [paper] [ Show Abstract ]

58. Matroid and Knapsack Center Problems. Danny Z. Chen, Jian Li, Hongyu Liang, and Haitao Wang. In The 16th Conference on Integer Programming and Combinatorial Optimization (IPCO 2013), Chile, 2013 [Paper] [Full version in ArXiv]. Journal version in Algorithmica, 2015. [ Show Abstract ]

59. Ranking Continuous Probabilistic Datasets. Jian Li and Amol Deshpande. In the 36th International Conference on Very Large Data Bases (VLDB 2010), Singapore, 2010. [Paper] [slides] [ Show Abstract ]

60. Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks. Binghui Li, Zhixuan Pan, Kaifeng Lyu, Jian Li. 2024. The 9th International Conference on Learning Representations (ICLR 2025).  [ArXiv][Openreview][ Show Abstract ]

61. When LP is the Cure for Your Matching Woes: Improved Bounds for Stochastic Matchings. Nikhil Bansal, Anupam Gupta, Jian Li, Julian Mestre, Viswanath Nagarajan, Atri Rudra. In the 18th Annual European Symposium on Algorithms (ESA 2010). (Best Paper Award) [Paper] [Slides] Journal version in Algorithimca, 2011.[Journal Version] [ Show Abstract ]

62. Algorithms on Minimizing the Maximum Sensor Movement for Barrier Coverage of a Linear Domain; Danny Z. Chen, Yan Gu, Jian Li and Haitao Wang; [ArXiv]. Journal version in Discrete Computational Geometry (DCG), 2013 [Journal doi] [ Show Abstract ]

63. MetaTrader: An reinforcement learning approach integrating diverse policies for portfolio optimization. Hui Niu, Siyuan Li, Jian Li. Proceedings of the 31st ACM international conference on information and knowledge management (CIKM 2023) [Paper] [ Show Abstract ]

64. Pure Exploration of Multi-armed Bandit Under Matroid Constraints. Lijie Chen, Anupum Gupta, Jian Li. Conference on Learning Theory (COLT 2016). [Full version] [ Show Abstract ]

65. Stochastic Gradient Hamiltonian Monte Carlo with Variance Reduction for Bayesian Inference. Zhize Li, Tianyi Zhang, Shuyu Cheng, Jun Zhu, Jian Li. Machine Learning, 2019. [ArXiv] [ Show Abstract ]

66. Odd Yao-Yao Graphs are Not Spanners. Yifei Jin, Jian Li, Wei Zhan. In 34th International Symposium on Computational Geometry (SoCG 2018). [ArXiv] [ Show Abstract ]

67. Almost All Even Yao-Yao Graphs Are Spanners. Jian Li, Wei Zhan. The 24rd Annual European Symposium on Algorithms (ESA 2016). [ArXiv] [ Show Abstract ]

68. Demand Driven Store Placement via Multiple Spatial-temporal Data. Mengwen Xu, Tianyi Wang, Zhengwei Wu, Jingbo Zhou, Jian Li and Haishan Wu. ACM SIGSPATIAL 2016. [paper][ Show Abstract ]

69. Clustering with Diversity. Jian Li, Ke Yi, Qin Zhang. In the 37th International Colloquium on Automata, Languages and Programming (ICALP 2010),July 5-10, 2010. [full version in arXiv] [ Show Abstract ]

70. Your Friends Have More Friends Than You Do: Identifying Influential mobiles Users Through Random Walks. Bo Han, Jian Li and Aravind Srinivasan. IEEE/ACM Transactions on Networking (TON), 2013 [Paper] [ Show Abstract ]

71. On Optimal Coreset Construction for (k,z)-Clustering. Lingxiao Huang, Jian Li, Xuan Wu. The 56th ACM Symposium on Theory of Computing (STOC 2024). [ArXiv] [ Show Abstract ]

72. DataSynth: Generating Synthetic Data using Declarative Constraints. Arvind Arasu, Raghav Kaushik, and Jian Li. In the 37th International Conference on Very Large Data Bases (VLDB 2011), Seattle, Wasington, 2011. (Demo)

73. Generative Table Pre-training Empowers Models for Tabular Prediction. Tianping Zhang, Shaowen Wang, Shuicheng Yan, Li Jian, Qian Liu. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023). [Paper][Github] [ Show Abstract ]

74. Approximating the Expected Values for Combinatorial Optimization Problems over Stochastic Points. Lingxiao Huang, Jian Li. The 42nd International Colloquium on Automata, Languages, and Programming (ICALP 2015). [ArXiv] [ Show Abstract ]

75. Latent Consistency Models: Synthesizing High-Resolution Images with Few-step Inference. Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, Hang Zhao. 2023. [Paper][Github][Huggingface][LCM-Lora][ Show Abstract ]

76. Scalable Column Concept Determination for Web Tables Using Large Knowledge Bases. Dong Deng, Yu Jiang, Guoliang Li, Jian Li, Cong Yu. In the 39th International Conference on Very Large Data Bases (VLDB 2013), Italy, 2013 [Paper][Full version].

77. NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization. Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang and Jie Tang. The 2019 Web Conference (WWW 2019, oral). [paper] [ Show Abstract ]

78. An $O({logn\over loglogn})$ Upper Bound on the Price of Stability for Undirected Shapley Network Design Games. Jian Li.In Information Processing Letter (IPL). 2009. [Paper][slides] [ Show Abstract ]

79. New Results on a General Class of Minimum Norm Optimization Problems. Kuowen Chen, Jian Li, Yuval Rabani, Yiran Zhang. The 52nd EATCS International Colloquium on Automata, Languages, and Programming (ICALP 2025). [ArXiv] [ Show Abstract ]

80. Coresets for clustering with general assignment constraints. Lingxiao Huang, Jian Li, Pinyan Lu, Xuan Wu. ACM-SIAM Symposium on Discrete Algorithms (SODA 2025). [ArXiv] [ Show Abstract ]

81. On the Energy Efficiency of Device Discovery in mobiles Opportunistic Networks: A Systematic Approach. Bo Han, Jian Li, Aravind Srinivasan. IEEE Transactions on mobiles Computing (TMC), 2014 [Paper]

82. A Pruned Exhaustive Search Algorithm for Nearly Optimal Diversified Result Ranking, Fei Chen, Yiqun Liu, Jian Li, Min Zhang and Shaoping Ma, 23rd International World Wide Web Conference, Seoul, Korea, April 7-11, 2014 (Poster)

83. Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization. Zhize Li, Jian Li. Journal of Machine Learning Research (JMLR), 2022. [ArXiv] [ Show Abstract ]

    We propose and analyze several stochastic gradient algorithms for finding stationary points or local minimum in nonconvex, possibly with nonsmooth regularizer, finite-sum and online optimization problems. First, we propose a simple proximal stochastic gradient algorithm based on variance reduction called ProxSVRG+. We provide a clean and tight analysis of ProxSVRG+, which shows that it outperforms the deterministic proximal gradient descent (ProxGD) for a wide range of minibatch sizes, hence solves an open problem proposed in~\citet{reddi2016proximal}. Also, ProxSVRG+ uses much less proximal oracle calls than ProxSVRG (Reddi et al. 2016) and extends to the online setting by avoiding full gradient computations. Then, we further propose an optimal algorithm, called SSRGD, based on SARAH (Nguyen et al. 2017) and show that SSRGD further improves the gradient complexity of ProxSVRG+ and achieves the the optimal upper bound, matching the known lower bound. Moreover, we show that both ProxSVRG+ and SSRGD enjoy automatic adaptation with local structure of the objective function such as the Polyak-\L ojasiewicz (PL) condition for nonconvex functions in the finite-sum case, i.e., we prove that both of them can automatically switch to faster global linear convergence without any restart performed in prior work ProxSVRG. Finally, we focus on the more challenging problem of finding an $(\epsilon, \delta)$-local minimum instead of just finding an $\epsilon$-approximate (first-order) stationary point (which may be some bad unstable saddle points). We show that SSRGD can find an $(\epsilon, \delta)$-local minimum by simply adding some random perturbations. Our algorithm is almost as simple as its counterpart for finding stationary points, and achieves similar optimal rates.

84. DeepScalper: A Risk-Aware Reinforcement Learning Framework to Capture Fleeting Intraday Trading Opportunities. Shuo Sun, Rundong Wang, Wanqi Xue, Xu He, Junlei Zhu, Jian Li and Bo An. The 31st ACM International Conference on Information and Knowledge Management (CIKM 2022). [ Show Abstract ]

    Reinforcement learning (RL) techniques have shown great success in many challenging quantitative trading tasks, such as portfolio management and algorithmic trading. Especially, intraday trading is one of the most profitable and risky tasks because of the intraday behaviors of the financial market that reflect billions of rapidly fluctuating capitals. However, a vast majority of existing RL methods focus on the relatively low frequency trading scenarios (e.g., day-level) and fail to capture the fleeting intraday investment opportunities due to two major challenges: 1) how to effectively train profitable RL agents for intraday investment decision-making, which involves high-dimensional fine-grained action space; 2) how to learn meaningful multi-modality market representation to understand the intraday behaviors of the financial market at tick-level. Motivated by the efficient workflow of professional human intraday traders, we propose DeepScalper, a deep reinforcement learning framework for intraday trading to tackle the above challenges. Specifically, DeepScalper includes four components: 1) a dueling Q-network with action branching to deal with the large action space of intraday trading for efficient RL optimization; 2) a novel reward function with a hindsight bonus to encourage RL agents making trading decisions with a long-term horizon of the entire trading day; 3) an encoder-decoder architecture to learn multi-modality temporal market embedding, which incorporates both macro-level and micro-level market information; 4) a risk-aware auxiliary task to maintain a striking balance between maximizing profit and minimizing risk. Through extensive experiments on real-world market data spanning over three years on six financial futures (2 stock index and 4 treasury bond), we demonstrate that DeepScalper significantly outperforms many state-of-the-art baselines in terms of four financial criteria. Furthermore, we conduct a series of exploratory and ablative studies to analyze the contributions of each component in DeepScalper.

85. Integrating Diverse Policies for Portfolio Management via Combining Imitation Learning and Reinforcement Learning. Hui Niu, Siyuan Li and Jian Li. The 31st ACM International Conference on Information and Knowledge Management (CIKM 2022). [ Show Abstract ]

    Portfolio management is a fundamental problem in finance. It involves periodic reallocations of assets to maximize the expected returns within an appropriate level of risk exposure. Deep reinforcement learning (RL) has been considered a promising approach to solving this problem owing to its strong ability in sequential decision making. However, due to the non-stationary nature of financial markets, applying RL techniques to portfolio optimization remains a challenging problem. Extracting trading knowledge from various expert strategies could be helpful for agents to accommodate the changing markets. In this paper, we propose \textit{MetaTrader}, a novel two-stage RL-based approach for portfolio management, which learns to integrate diverse trading policies to adapt to various market conditions. In the first stage, MetaTrader incorporates an imitation learning objective into the reinforcement learning framework. Through imitating different expert demonstrations, MetaTrader acquires a set of trading policies with great diversity. In the second stage, MetaTrader learns a meta-policy to recognize the market conditions and decide on the most proper learned policy to follow. We evaluate the proposed approach on three real-world index datasets and compare it to state-of-the-art baselines. The empirical results demonstrate that MetaTrader significantly outperforms those baselines in balancing profits and risks. Furthermore, thorough ablation studies validate the effectiveness of the components in the proposed approach.

86. Analyzing and Mitigating Interference in Neural Architecture Search. Jin Xu, Xu Tan, Kaitao Song, Renqian Luo, Yichong Leng, Tao Qin, Tie-Yan Liu, Jian Li. The 39th International Conference on Machine Learning (ICML 2022, spotlight) [ Show Abstract ]

    Weight sharing is a popular approach to reduce the cost of neural architecture search (NAS) by reusing the weights of shared operators from previously trained child models. However, the rank correlation between the estimated accuracy and ground truth accuracy of those child models is low due to the interference among different child models caused by weight sharing. In this paper, we investigate the interference issue by sampling different child models and calculating the gradient similarity of shared operators, and observe: 1) the interference on a shared operator between two child models is positively correlated with the number of different operators; 2) the interference is smaller when the inputs and outputs of the shared operator are more similar. Inspired by these two observations, we propose two approaches to mitigate the interference: 1) MAGIC-T: rather than randomly sampling child models for optimization, we propose a gradual modification scheme by modifying one operator between adjacent optimization steps to minimize the interference on the shared operators; 2) MAGIC-A: forcing the inputs and outputs of the operator across all child models to be similar to reduce the interference. Experiments on a BERT search space verify that mitigating interference via each of our proposed methods improves the rank correlation of super-pet and combining both methods can achieve better results. Our discovered architecture outperforms RoBERTa by 1.1 and 0.6 points and ELECTRA by 1.6 and 1.1 points on the dev and test set of GLUE benchmark. Extensive results on the BERT compression, reading comprehension and ImageNet task demonstrate the effectiveness and generality of our proposed methods.

87. FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-sectional Stock Returns. Yitong Duan, Lei Wang, Qizhong Zhang, Jian Li. AAAI Conference on Artificial Intelligence (AAAI 2022). [ Show Abstract ]

    As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment. Towards building more effective factor models, recent years have witnessed the paradigm shift from linear models to more flexible nonlinear data-driven machine learning models. However, due to low signal-to-noise ratio of the financial data, it is quite challenging to learn effective factor models. In this paper, we propose a novel factor model, FactorVAE, as a probabilistic model with inherent randomness for noise modeling. Essentially, our model integrates the dynamic factor model (DFM) with the variational autoencoder (VAE) in machine learning, and we propose a prior-posterior learning method based on VAE, which can effectively guide the learning of model by approximating an optimal posterior factor model with future information. Particularly, considering that risk modeling is important for the noisy stock data, FactorVAE can estimate the variances from the distribution over the latent space of VAE, in addition to predicting returns. The experiments on the real stock market data demonstrate the effectiveness of FactorVAE, which outperforms various baseline methods.

88. FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning. Jing Zhou, Yanan Zheng, Jie Tang, Jian Li, and Zhilin Yang. 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022). [ArXiv] [ Show Abstract ]

    Most previous methods for text data augmentation are limited to simple tasks and weak baselines. We explore data augmentation on hard tasks (i.e., few-shot natural language understanding) and strong baselines (i.e., pretrained models with over one billion parameters). Under this setting, we reproduced a large number of previous augmentation methods and found that these methods bring marginal gains at best and sometimes degrade the performance much. To address this challenge, we propose a novel data augmentation method FlipDA that jointly uses a generative model and a classifier to generate label-flipped data. Central to the idea of FlipDA is the discovery that generating label-flipped data is more crucial to the performance than generating label-preserved data. Experiments show that FlipDA achieves a good tradeoff between effectiveness and robustness--- it substantially improves many tasks while not negatively affecting the others.

89. FewNLU: Benchmarking state-of-the-art methods for few-shot natural language understanding. Zheng, Yanan, Jing Zhou, Yujie Qian, Ming Ding, Jian Li, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, and Zhilin Yang. 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022). [ArXiv] [ Show Abstract ]

    The few-shot natural language understanding (NLU) task has attracted much recent attention. However, prior methods have been evaluated under a disparate set of protocols, which hinders fair comparison and measuring progress of the field. To address this issue, we introduce an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability. Under this new evaluation framework, we re-evaluate several state-of-the-art few-shot methods for NLU tasks. Our framework reveals new insights: (1) both the absolute performance and relative gap of the methods were not accurately estimated in prior literature; (2) no single method dominates most tasks with consistent performance; (3) improvements of some methods diminish with a larger pretrained model; and (4) gains from different methods are often complementary and the best combined model performs close to a strong fully-supervised baseline. We open-source our toolkit, FewNLU, that implements our evaluation framework along with a number of state-of-the-art methods.

90. Synthesizing Entity Resolution Datasets. Xuedi Qin, Chengliang Chai, Nan Tang,Jian Li, Yuyu Luo, Guoliang Li, Yaoyu Zhu. The 38th IEEE International Conference on Data Engineering (ICDE 2022). [ Show Abstract ]

    Entity resolution (ER) is a core problem in data integration. Many companies have lots of datasets where ER needs to be conducted to integrate the data. On the one hand, it is nontrivial for non-ER experts within companies to design ER solutions. On the other hand, most companies are reluctant to release their real datasets for multiple reasons (e.g., privacy issues). A typical solution from the machine learning (ML) and the statistical community is to create surrogate (a.k.a. analogous) datasets based on the real dataset, release these surrogate datasets to the public to train ML models, such that these models trained on surrogate datasets can be either directly used or be adapted for the real dataset by the companies. In this paper, we study a new problem of synthesizing surrogate ER datasets using transformer models, with the goal that the ER model trained on the synthesized dataset can be used directly on the real dataset. We propose methods to solve this problem: we first learn the true similarity distributions of both matching and non-matching entity pairs from real dataset. We then devise algorithms that can synthesize fake but semantically meaningful entities, add matching and non-matching labels to these fake entity pairs, and ensure that the fake and real datasets have similar distributions. We also describe a method for entity rejection to avoid synthesizing bad fake entities that may destroy the original distributions. Extensive experiments show that ER matchers trained on real and synthetic ER datasets have very close performance on the same test sets C their F1 scores differ within 6% on 3 commonly used ER datasets, and their average precision, recall differences are less than 5%.

91. AutoHEnsGNN: Winning Solution to AutoGraph Challenge for KDD Cup 2020. Jin Xu, Mingjian Chen, Jianqiang Huang, Tangxing Yuan, Ke Hu, Jian Li, Jia Cheng, Jun Lei. The 38th IEEE International Conference on Data Engineering (ICDE 2022). [paper] [ Show Abstract ]

    Graph Neural Networks (GNNs) have become increasingly popular and achieved impressive results in many graph-based applications. However, extensive manual work and domain knowledge are required to design effective architectures, and the results of GNN models have high variance with different training setups, which limits the application of existing GNN models. In this paper, we present AutoHEnsGNN, a framework to build effective and robust models for graph tasks without any human intervention. AutoHEnsGNN won first place in the AutoGraph Challenge for KDD Cup 2020, and achieved the best rank score of five real-life datasets in the final phase. Given a task, AutoHEnsGNN first applies a fast proxy evaluation to automatically select a pool of promising GNN models. Then it builds a hierarchical ensemble framework: 1) We propose graph self-ensemble (GSE), which can reduce the variance of weight initialization and efficiently exploit the information of local and global neighborhoods; 2) Based on GSE, a weighted ensemble of different types of GNN models is used to effectively learn more discriminative node representations. To efficiently search the architectures and ensemble weights, we propose AutoHEnsGNN$_{\text{Gradient}}$, which treats the architectures and ensemble weights as architecture parameters and uses gradient-based architecture search to obtain optimal configurations, and AutoHEnsGNN$_{\text{Adaptive}}$, which can adaptively adjust the ensemble weight based on the model accuracy. Extensive experiments on KDD Cup datasets and commonly used datasets Cora, Citeseer, Pubmed and ogbn-arxiv demonstrate the effectiveness and robustness of AutoHEnsGNN.

92. Multi-token Markov Game with Switching Costs. Jian Li, Daogao Liu. ACM-SIAM Symposium on Discrete Algorithms (SODA22). [paper] [ Show Abstract ]

    We study a general Markov game with metric switching costs: in each round, the player adaptively chooses one of several Markov chains to advance with the objective of minimizing the expected cost for at least k chains to reach their target states. If the player decides to play a different chain, an additional switching cost is incurred. The special case in which there is no switching cost was solved optimally by Dumitriu, Tetali, and Winkler [DTW03] by a variant of the celebrated Gittins Index for the classical multi-armed bandit (MAB) problem with Markovian rewards [Gittins 74, Gittins79]. However, for multi-armed bandit (MAB) with nontrivial switching cost, even if the switching cost is a constant, the classic paper by Banks and Sundaram [BS94] showed that no index strategy can be optimal. In this paper, we complement their result and show there is a simple index strategy that achieves a constant approximation factor if the switching cost is constant and k=1. To the best of our knowledge, this is the first index strategy that achieves a constant approximation factor for a general MAB variant with switching costs. For the general metric, we propose a more involved constant-factor approximation algorithm, via a nontrivial reduction to the stochastic k-TSP problem, in which a Markov chain is approximated by a random variable. Our analysis makes extensive use of various interesting properties of the Gittins index.

93. Simple Combinatorial Algorithms for Combinatorial Bandits: Corruptions and Approximations. Haike Xu, Jian Li. Uncertainty in Artificial Intelligence (UAI 2021). [paper] [ Show Abstract ]

    We consider the stochastic combinatorial semi-bandit problem with adversarial corruptions.

94. NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search. Jin Xu, Xu Tan, Renqian Luo, Kaitao Song, Jian Li, Tao Qin, Tie-Yan Liu. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD 2021). [paper] [ Show Abstract ]

    While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer from big computational and memory costs, which make them difficult for real-world deployment. Therefore, model compression is necessary to reduce the computation and memory cost of pre-trained models. In this work, we aim to compress BERT and address the following two challenging practical issues: (1) The compression algorithm should be able to output multiple compressed models with different sizes and latencies, in order to support devices with different memory and latency limitations; (2) The algorithm should be downstream task agnostic, so that the compressed models are generally applicable for different downstream tasks. We leverage techniques in neural architecture search (NAS) and propose NAS-BERT, an efficient method for BERT compression. NAS-BERT trains a big supernet on a search space containing a variety of architectures and outputs multiple compressed models with adaptive sizes and latency. Furthermore, the training of NAS-BERT is conducted on standard self-supervised pre-training tasks (e.g., masked language model) and does not depend on specific downstream tasks. Thus, the compressed models can be used across various downstream tasks. The technical challenge of NAS-BERT is that training a big supernet on the pre-training task is extremely costly. We employ several techniques including block-wise search, search space pruning, and performance approximation to improve search efficiency and accuracy. Extensive experiments on GLUE and SQuAD benchmark datasets demonstrate that NAS-BERT can find lightweight models with better accuracy than previous approaches, and can be directly applied to different downstream tasks with adaptive model sizes for different requirements of memory or latency.

95. Return-Based Contrastive Representation Learning for Reinforcement Learning. Guoqing Liu, Chuheng Zhang, Li Zhao, Tao Qin, Jinhua Zhu, Li Jian, Nenghai Yu, Tie-Yan Liu. 2021 International Conference on Learning Representations (ICLR2021) [paper] [ Show Abstract ]

    Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems into consideration and are unsupervised. By leveraging returns, the most important feedback signals in RL, we propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our auxiliary loss is theoretically justified to learn representations that capture the structure of a new form of state-action abstraction, under which state-action pairs with similar return distributions are aggregated together. Empirically, our algorithm outperforms strong baselines on complex tasks in Atari games and DeepMind Control suite, and achieves even better performance when combined with existing auxiliary tasks.

96. Exploration by Maximizing Renyi Entropy for Reward-Free RL Framework. Chuheng Zhang, Yuanying Cai, Longbo Huang, Jian Li. AAAI Conference on Artificial Intelligence (AAAI 2021). [ArXiv] [ Show Abstract ]

    we consider a reward free meta RL framework that completely separates exploration from exploitation and is suitable for the meta RL setting where there are many reward functions of interest. In the exploration phase, the agent learns an exploratory policy by interacting with a reward-free environment and collects a dataset of transitions by executing the policy. In the planning phase, the agent computes a good policy for any reward function based on the dataset without further interacting with the environment. This framework brings new challenges for exploration algorithms. In the exploration phase, we propose to maximize the R nyi entropy over the state-action space and justify this objective theoretically. We further deduce a policy gradient formulation for this objective and design a practical exploration algorithm that can deal with complex environments based on PPO. In the planning phase, we use a batch RL algorithm, batch constrained deep Q-learning (BCQ), to solve for good policies given arbitrary reward functions. Empirically, we show that our exploration algorithm is effective and sample efficient, and results in superior policies for arbitrary reward functions in the planning phase.

97. Improved Algorithms for Convex-Concave Minimax Optimization, Yuanhao Wang, Jian Li. 2020 Conference on Neural Information Processing Systems (NeurIPS 2020). [ArXiv] [ Show Abstract ]

    This paper studies minimax optimization problems min_x max_y f(x,y), where f(x,y) is mx-strongly convex with respect to x, my-strongly concave with respect to y and (Lx,Lxy,Ly)-smooth. This paper proposes a new algorithm with better gradient complexity upper bound, which improves over the best known upper bound by Lin et al. Our bound achieves linear convergence rate and tighter dependency on condition numbers, especially when Lxy≪L (i.e., when the interaction between x and y is weak). Via reduction, our new bound also implies improved bounds for strongly convex-concave and convex-concave minimax optimization problems. When f is quadratic, we can further improve the upper bound, which matches the lower bound up to a small sub-polynomial factor.

98. DoubleEnsemble: A New Ensemble Method Based on Sample Reweighting and Feature Selection for Financial Data Analysis. Chuhang Zhang, Yuanqi Li, Xi Chen, Yifei Jin, Pingzhong Tang, Jian Li. The IEEE International Conference on Data Mining (ICDM 2020). [ArXiv] [ Show Abstract ]

    Modern machine learning models (such as deep neural networks and boosting decision tree models) have become increasingly popular in financial market prediction, due to their superior capacity to extract complex non-linear patterns. However, since financial datasets have very low signal-to-noise ratio and are non-stationary, complex models are often very prone to overfitting and suffer from instability issues. Moreover, as various machine learning and data mining tools become more widely used in quantitative trading, many trading firms have been producing an increasing number of features (aka factors). Therefore, how to automatically select effective features becomes an imminent problem. To address these issues, we propose DoubleEnsemble, an ensemble framework leveraging learning trajectory based sample reweighting and shuffling based feature selection. Specifically, we identify the key samples based on the training dynamics on each sample and elicit key features based on the ablation impact of each feature via shuffling. Our model is applicable to a wide range of base models, capable of extracting complex patterns, while mitigating the overfitting and instability issues for financial market prediction. We conduct extensive experiments, including price prediction for cryptocurrencies and stock trading, using both DNN and gradient boosting decision tree as base models. Our experiment results demonstrate that DoubleEnsemble achieves a superior performance compared with several baseline methods.

99. Approximation Algorithms for Clustering with Dynamic Points. Deng, Shichuan, Jian Li, and Yuval Rabani. The European Symposium on Algorithms (ESA 2020). Journal version in Journal of Computer and System Sciences, 2022 [ArXiv] [ Show Abstract ]

100. ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classification. Liang Zeng, Lanqing Li, Ziqi Gao, Pinlin Zhao, Jian Li. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023) [Paper] [ Show Abstract ]

101. DeepSD: Supply-Demand Prediction for Online Car-hailing Services using Deep Neural Networks. Dong Wang, Wei Cao, Jian Li, Jieping Ye. The 33th IEEE International Conference on Data Engineering (ICDE 2017). [paper] [ Show Abstract ]

102. The Multi-shop Ski Rental Problem, Lingqing Ai, Xian Wu, Lingxiao Huang, Longbo Huang, Pingzhong Tang, and Jian Li, Proceedings of ACM SIGMETRICS, 2014. [paper]

103. BRITS: Bidirectional Recurrent Imputation for Time Series. Wei Cao, Dong Wang,Jian Li, Hao Zhou, Lei Li, Yitan Li. Thirty-second Conference on Neural Information Processing Systems (NeurIPS 2018) [paper] [ Show Abstract ]

104. Learning Gradient Descent: Better Generalization and Longer Horizons. Kaifeng Lv, Shunhua Jiang, Jian Li. The 34th International Conference on Machine Learning (ICML 2017). [ArXiv] [ Show Abstract ][Code]

105. A Unified Approach to Ranking in Probabilistic Databases. Jian Li, Barna Saha and Amol Deshpande. In the 35th International Conference on Very Large Data Bases (VLDB 2009), Lyon, France, 2009. (Best Paper Award) [Paper] [Slides long short] Journal version: The VLDB Journal, 2011. [Journal Version] [ Show Abstract ]

106. More Efficient Algorithms and Analyses for Unequal Letter Cost Prefix-Free Coding. Mordecai Golin, Jian Li. In IEEE Transactions on Information Theory, Volume 54, Issue 8, Aug. Page(s):3412 - 3424, 2008 [Journal Version] [ Show Abstract ]

107. IMM: An Imitative Reinforcement Learning Approach with Predictive Representation Learning for Automatic Market Making Hui Niu, Siyuan Li, Jiahao Zheng, Zhouchi Lin, Jian Li, Jian Guo, Bo An. The 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024). [Paper] [ Show Abstract ]

108. Efficient Algorithms for Sparse Moment Problems without Separation. Zhiyuan Fan, Jian Li. The 36th Annual Conference on Learning Theory (COLT 2023). [ArXiv] [ Show Abstract ]

109. Stochastic Combinatorial Optimization via Poisson Approximation. Jian Li and Wen Yuan. In the 45th ACM Symposium on the Theory of Computing (STOC 2013), USA,2013 [Paper] [Full version in ArXiv] [ Show Abstract ]

110. New Models and Algorithms for Throughput Maximization in Broadcast Scheduling. Chandra Chekuri, Avigdor Gal, Sungjin Im, Samir Khuller, Jian Li, Richard McCutchen, Benjamin Moseley, Louiqa Raschid. In the 8th Workshop on Approximation and Online Algorithms (WAOA 2010). [slides] [full version]

111. Approximation Algorithms for the Connected Sensor Cover Problem. Lingxiao Huang, Jian Li, Qicai Shi. Theoretical Computer Science (TCS 2020). Preliminary version appeared in The 21st Annual International Computing and Combinatorics Conference (COCOON'15) (in the conference version, the construction of the steiner tree LP and lemma 4 have some problems. please read the journal version here) [paper] [ Show Abstract ]

112. Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models. Qiong Wu, Jian Li, Zhenming Liu, Yanhua Li, Mihai Cucuringu. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023) [Paper] [ Show Abstract ]

113. Algorithms and Adaptivity Gaps for Stochastic k-TSP. Haotian Jiang, Jian Li, Daogao Liu, Sahil Singla. The 11th Innovations in Theoretical Computer Science (ITCS 2020). [ArXiv] [ Show Abstract ]

114. FactorGCL: A Hypergraph-Based Factor Model with Temporal Residual Contrastive Learning for Stock Returns Prediction. Yitong Duan, Weiran Wang, Jian Li. The Thirty-ninth AAAI Conference on Artificial Intelligence (AAAI 2025) [ArXiv] [ Show Abstract ]

115. AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-series Generation. Lei Wang, Liang Zeng, Jian Li. The Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023) [Paper] [ Show Abstract ]

116. Minimizing communication cost in distributed multi-query processing. Jian Li, Amol Deshpande and Samir Khuller. In International Conference on Data Engineering (ICDE2009), Shanghai, China, 2009 [Paper] [slides] [ Show Abstract ]

117. Densest $k$-Subgraph Approximation on Intersection Graphs. Danny Z. Chen, Rudolf Fleischer, Jian Li. In the 8th Workshop on Approximation and Online Algorithms (WAOA 2010). [Paper][slides] [ Show Abstract ]

118. The load-distance balancing problem. Edward Bortnikov, Samir Khuller, Jian Li, Yishay Mansour and Seffi Naor. Networks, 2012. [Paper] [doi] [ Show Abstract ]

119. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec. Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang. The 11th ACM International Conference on Web Search and Data Mining (WSDM 2018). [ArXiv] [ Show Abstract ]

120. LoRA-GA: Low-Rank Adaptation with Gradient Approximation. Shaowen Wang, Linxi Yu, Jian Li. Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2024). [ArXiv] [Github] [Lora-GA in PEFT][ Show Abstract ]

121. Optimal In-Place Suffix Sorting. Zhize Li, Jian Li, Hongwei Huo. Journal version in Information and Computation (I&C) 2021. [Full version in ArXiv] [ Show Abstract ]

122. Combinatorial Multi-Armed Bandit with General Reward Functions, Wei Chen, Wei Hu, Fu Li, Jian Li, Yu Liu, Pinyan Lu. Neural Information Processing Systems (NIPS 2016, Oral). [Full version in ArXiv] [ Show Abstract ]