Hongyang (Ryan) Zhang Assistant Professor, Computer Science Northeastern University Boston, MA 02115 Address: 177 Huntington Ave FL 22nd, Room #2211 Email: ho.zhang@northeastern.edu

I am an Assistant Professor of Computer Science at Northeastern University, Boston. My research interests lie at the intersection of machine learning, algorithms, statistical learning theory, and data mining, including topics such as:

• Efficient learning algorithms for using and fine-tuning neural networks, as well as understanding the generalization properties of neural networks with complex struccture by examining the Hessian.

• Efficient foundation models, mostly focusing on multitask learning and fine-tuning.

• Learning with graph-structured data, including an application to studying traffic accident patterns on the road.

I received my Ph.D. in computer science from Stanford and my B.Eng. in computer science from Shanghai Jiao Tong University. I spent about a year as a postdoc within the statistics and data science department at University of Pennsylvania. For more information about me, please look at my cv.

I enjoy working on technically challenging problems, and strive for broader impacts by creating new knowledge and improving access to education. I support accessible and reproducible research. See our experiment codes on GitHub. Here is a list of my recent activities.

Research

• Research papers

• Publications by year

Generalization of neural networks, optimization algorithms, statistical learning theory (talk slides):

• 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
  

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

• 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
  

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

Foundation models, multitask learning, fine-tuning (some recent talk slides):

• 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
  

• 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
  

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

Manuscripts

• Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers. F. Yang, H. R. Zhang, S. Wu, C. Ré, and W. Su
  

You may also see my Google Scholar for publication information.

Teaching

• DS 5220, Supervised Machine Learning and Learning Theory, Fall 2021, Fall 2022, Fall 2024.

• CS 6140, Machine Learning, Fall 2023.

• CS 7140, Advanced Machine Learning, Spring 2021, Spring 2022, Spring 2023.

• DS 4400, Machine Learning and Data Mining I, Spring 2023.

• CS 7180, Special Topics in Artificial Intelligence (Algorithmic and Statistical Aspects of Deep Learning), Fall 2020.

Lab

Link to our lab page. Here is a list of current, active lab members:

• Dongyue Li, PhD

• Ziniu (Michael) Zhang, PhD

• Zhenshuo Zhang, PhD

• Haotian Ju, MS RA

• Abhinav Nippani, MS RA

Prospective students: Please take a look at labpage and github. Students with a strong background in mathematics or programming are generally a good fit for conducting the projects. If you are interested, please contact me at hongyang90@gmail.com.

Students who wish to visit me at 177: Note that this building has access control. If you plan to visit me in-person, you should confirm the scheduled time with me before arrival so that I could give you permission to enter the building at the security.

Professional Services

Program Committee Member: ICML (2019-2023; meta-reviewer, 2024), NeurIPS (2019-2024), ICLR (2021-2024), COLT (2024), AISTATS (2021-2022; meta-reviewer, 2023-2025), ALT (meta-reviewer, 2024), KDD (2023-2024), AAAI (2020-2022; meta-reviewer, 2025), WWW 2022, WSDM (2022-2024).

External Conference/Journal Reviewer: STOC (2017, 2018, 2022), FOCS (2015, 2024), SODA (2016, 2021), ITCS (2018, 2019), WINE (2014), ICALP (2014). IEEE Transactions on Information Theory (2022), JMLR (2022), TMLR (2023-).

Conference Organization: INFORMS session chair (2023-2024).

Education/Experience

• October 2019 to July 2020: Postdoctoral Researcher, University of Pennsylvania

• September 2013 to September 2019: Ph.D., Stanford University

• July 2012 to July 2013: Research Assistant, Nanyang Technological University

• September 2008 to September 2012: B.Eng., Shanghai Jiao Tong University

My Chinese name is written as 张泓洋.