Research papers

Link to DBLP and Google Scholar. You can find the code for reproducing our empirical work in the following GitHub. Acknowledgement: Our research has been generously supported by funds from the National Science Foundation and from JP Morgan Chase.

By year | By topic | Selected papers

Optimization for ML and RL

1. WinQ: Accelerating Quantization-Aware Training of Language Models around Saddle Points
   D. Li, Z. Liu, K. Yi, Z. Zhang, C. Zhao, R. Krishnamoorthi, H. Khaitan, H. R. Zhang, and S. Li
   International Conference on Machine Learning (ICML), 2026

2. One-Sided Matrix Completion from Ultra-Sparse Samples
   H. R. Zhang, Z. Zhang, H. L. Nguyen, and G. Lan
   Transactions on Machine Learning Research (TMLR), 2026. Featured Certification
   

3. Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
   Z. Zhang, M. Duan, Y. Ye, and H. R. Zhang
   AAAI, 2026
   

4. Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
   H. R. Zhang, D. Li, and H. Ju
   Transactions on Machine Learning Research (TMLR), 2024
   

Statistical Learning Theory

1. Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers
   F. Yang*, H. R. Zhang*, S. Wu, C. Ré, and W. Su
   Journal of Machine Learning Research (JMLR), 2025
   

2. Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
   H. Ju, D. Li, A. Sharma, and H. R. Zhang
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2023

3. Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
   H. Ju, D. Li, and H. R. Zhang
   International Conference on Machine Learning (ICML), 2022
   

4. On the Generalization Effects of Linear Transformations in Data Augmentation
   S. Wu*, H. R. Zhang*, G. Valiant, and C. Ré
   International Conference on Machine Learning (ICML), 2020
   

5. Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK
   Y. Li, T. Ma, and H. R. Zhang*
   Conference on Learning Theory (COLT), 2020
   

6. Recovery Guarantees for Quadratic Tensors with Sparse Observations
   H. R. Zhang, V. Sharan, M. Charikar, and Y. Liang
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

7. Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
   Y. Li, T. Ma, and H. R. Zhang*
   Conference on Learning Theory (COLT), 2018. Best Paper Award

Neural Networks and Foundation Models

1. Efficient Estimation of Kernel Surrogate Models for Task Attribution
   Z. Zhang, M. Duan, and H. R. Zhang
   International Conference on Learning Representations (ICLR), 2026

2. Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
   D. Li, Z. Zhang, M. Duan, E. Dobriban, and H. R. Zhang
   To appear in KDD, 2026

3. Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimation
   Z. Zhang*, Z. Zhang*, D. Li, L. Wang, J. Dy, and H. R. Zhang
   Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
   

4. Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets
   D. Li, Z. Zhang, L. Wang, and H. R. Zhang
   Association for Computational Linguistics (ACL), 2025
   

5. Scalable Fine-tuning From Multiple Data Sources: A First-order Approximation Approach
   D. Li, Z. Zhang, L. Wang, and H. R. Zhang
   Findings of Empirical Methods in Natural Language Processing (Findings of EMNLP), 2024
   

6. Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
   D. Li, A. Sharma, and H. R. Zhang
   ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2024
   

7. Learning Tree-Structured Composition of Data Augmentation
   D. Li, K. Chen, P. Radivojac, and H. R. Zhang
   Transactions on Machine Learning Research (TMLR), 2024
   

8. Improved Group Robustness via Classifier Retraining on Independent Splits
   T. H. Nguyen, H. R. Zhang, and H. L. Nguyen
   Transactions on Machine Learning Research (TMLR), 2023

9. Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
   D. Li, H. Ju, A. Sharma, and H. R. Zhang
   SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023

10. Identification of Negative Transfers in Multitask Learning using Surrogate Models
    D. Li, H. L. Nguyen, and H. R. Zhang
    Transactions on Machine Learning Research (TMLR), 2023. Featured Certification

11. Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
    M. Zhang, N. Sohoni, H. R. Zhang, C. Finn, and C. Ré
    International Conference on Machine Learning (ICML), 2022. Long presentation
    

12. Improved Regularization and Robustness for Fine-tuning in Neural Networks
    D. Li and H. R. Zhang
    Neural Information Processing Systems (NeurIPS), 2021
    

13. Observational Supervision for Medical Image Classification using Gaze Data
    K. Saab, S. Hooper, N. Sohoni, J. Parmar, B. Pogatchnik, S. Wu, J. Dunnmon, H. R. Zhang, D. Rubin, and C. Ré
    Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021
    

14. Understanding and Improving Information Transfer in Multi-Task Learning
    S. Wu*, H. R. Zhang*, and C. Ré
    International Conference on Learning Representations (ICLR), 2020
    

Large-Scale Networks

1. Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
   Z. Zhang, M. Duan, H. N. Koutsopoulos, and H. R. Zhang
   KDD, 2026 (Datasets and Benchmarks Track)

2. Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
   A. Nippani, D. Li, H. Ju, H. N. Koutsopoulos, H. R. Zhang
   NeurIPS, 2023 (Datasets and Benchmarks Track)

3. Optimal Intervention on Weighted Networks via Edge Centrality
   D. Li, T. Eliassi-Rad, and H. R. Zhang
   SIAM International Conference on Data Mining (SDM), 2023

4. Pruning based Distance Sketches with Provable Guarantees on Random Graphs
   H. R. Zhang, H. Yu, and A. Goel
   The Web Conference (WWW), 2019. Oral presentation
   [code]

5. Approximate Personalized PageRank on Dynamic Graphs
   H. R. Zhang, P. Lofgren, and A. Goel
   KDD 2016. Oral presentation
   [code]

6. A Note on Modeling Retweet Cascades on Twitter
   A. Goel, K. Munagala, A. Sharma, and H. R. Zhang*
   Workshop on Algorithms and Models for the Web Graph (WAW), 2015

7. Connectivity in Random Forests and Credit Networks
   A. Goel, S. Khanna, S. Raghvendra, and H. R. Zhang*
   Symposium on Discrete Algorithms (SODA), 2015

Algorithmic Game Theory

1. Incentive Ratio: A Game Theoretical Analysis of Market Equilibria
   N. Chen, X. Deng, B. Tang, H. R. Zhang, and J. Zhang
   Information and Computation, 2022

2. Incentives for Strategic Behavior in Fisher Market Games
   N. Chen, X. Deng, B. Tang, and H. R. Zhang*
   AAAI 2016

3. Computing the Nucleolus of Matching, Cover and Clique Games
   N. Chen, P. Lu, and H. R. Zhang*
   AAAI 2012. Oral presentation

4. Incentive Ratios of Fisher Markets
   N. Chen, X. Deng, H. R. Zhang*, and J. Zhang
   International Colloquium on Automata, Languages, and Programming (ICALP), 2012

5. On Strategy-proof Allocation without Payments or Priors
   L. Han, C. Su, L. Tang, and H. R. Zhang*
   Conference on Web and Internet Economics (WINE), 2011