Hongyang Zhang
(he/him/his)
Assistant Professor
Research interests
- Machine learning
- Design and analysis of algorithms
- Learning theory
- Data, data augmentation, and networks
- Language modeling
Education
- Postdoctorate in Statistics and Data Science, University of Pennsylvania
- PhD in Computer Science, Stanford University
- BEng in Computer Science, Shanghai Jiao Tong University — China
Biography
Hongyang (Ryan) Zhang is an assistant professor in the Khoury College of Computer Sciences at Northeastern University, based in Boston.
Zhang's research interests lie at the intersection of machine learning, design and analysis of algorithms, learning theory, data, networks, and language modeling. He spent a year as a postdoc in the statistics and data science department at the University of Pennsylvania; served as an area chair and program committee member for ICML, AISTATS, COLT, ALT, and AAAI; and served as an action editor for the Journal of Data-centric Machine Learning Research.
Labs and groups
Recent publications
-
Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
Citation: Dongyue Li, Aneesh Sharma, Hongyang R. Zhang. (2024). Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity KDD, 1542-1553. https://doi.org/10.1145/3637528.3671835 -
Learning Tree-Structured Composition of Data Augmentation
Citation: Dongyue Li, Kailai Chen, Predrag Radivojac, Hongyang R. Zhang. (2024). Learning Tree-Structured Composition of Data Augmentation Trans. Mach. Learn. Res., 2024. https://openreview.net/forum?id=lmgf03HeqV -
Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
Citation: Dongyue Li, Haotian Ju, Aneesh Sharma, Hongyang R. Zhang. (2023). Boosting Multitask Learning on Graphs through Higher-Order Task Affinities KDD, 1213-1222. https://doi.org/10.1145/3580305.3599265 -
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
Citation: Haotian Ju, Dongyue Li, Hongyang R. Zhang. (2022). Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees ICML, 10431-10461. https://proceedings.mlr.press/v162/ju22a.html -
Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations
Citation: Michael Zhang, Nimit Sharad Sohoni, Hongyang R. Zhang, Chelsea Finn, Christopher Ré. (2022). Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations ICML, 26484-26516. https://proceedings.mlr.press/v162/zhang22z.html -
Improved Regularization and Robustness for Fine-tuning in Neural Networks
Citation: Dongyue Li, Hongyang R. Zhang. (2021). Improved Regularization and Robustness for Fine-tuning in Neural Networks NeurIPS, 27249-27262. https://proceedings.neurips.cc/paper/2021/hash/e4a93f0332b2519177ed55741ea4e5e7-Abstract.html -
Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression
Citation: Zhang, H.R., Yang, F., Wu, S., Su, W.J. and Ré, C., 2020. Sharp Bias-variance Tradeoffs of Hard Parameter Sharing in High-dimensional Linear Regression. arXiv preprint arXiv:2010.11750. -
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK
Citation: Li, Y., Ma, T. and Zhang, H.R., 2020, July. Learning Over-parametrized Two-layer Neural Networks beyond NTK. In Conference on Learning Theory. -
On the Generalization Effects of Linear Transformations in Data Augmentation
Citation: Wu, S., Zhang, H.R., Valiant, G. and Ré, C., 2020. On the Generalization Effects of Linear Transformations in Data Augmentation. ICML. -
Understanding and Improving Information Transfer in Multi-Task Learning
Citation: Wu, S., Zhang, H.R. and Ré, C., 2020. Understanding and Improving Information Transfer in Multi-Task Learning. ICLR. -
Pruning based Distance Sketches with Provable Guarantees on Random Graphs
Citation: Zhang, H., Yu, H. and Goel, A., 2019, May. Pruning based Distance Sketches with Provable Guarantees on Random Graphs. In The World Wide Web Conference. -
Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations
Citation: Li, Y., Ma, T. and Zhang, H.R., 2018, July. Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations. In Conference On Learning Theory.
