معرفی
Yaoliang Yu is an Associate Professor in the Department of Computer Science at the University of Waterloo, Canada. He holds a Ph.D. from the University of Alberta (2013), and M.Sc. and B.Sc. degrees from Fudan University, China (2008 and 2005, respectively). His research focuses on Machine Learning, particularly generative models, representation learning, optimization algorithms, and applications in computer vision and natural language processing. He actively explores topics such as diffusion models, federated learning, adversarial robustness, and algorithmic fairness.
- Affiliations: School of Computer Science, University of Waterloo
- Key Research Areas: Generative Modelling, Optimization Theory, Federated Learning, Adversarial Machine Learning
Education:
- Ph.D. in Computer Science, University of Alberta (2013)
- M.Sc. in Computer Science, Fudan University (2008)
- B.Sc. in Computer Science, Fudan University (2005)
Research Interests: Yu’s work bridges theoretical foundations and practical applications in machine learning. His recent efforts emphasize robustness in generative models (e.g., diffusion models), optimization methods for non-convex problems, and privacy-preserving federated learning. He also investigates adversarial attacks and defenses, such as data poisoning and model unlearning mechanisms.
Publications: His recent work explores diffusion models with group equivariance, noise-aware federated learning, and convergence guarantees for optimization algorithms like Adam. These studies reflect a trend toward unifying theory and practice in scalable ML systems.
Awards: No awards explicitly listed in the provided text.
Advising & Grants: While specific grants are not detailed, his research portfolio suggests involvement in projects funded by Canadian NSERC or industry partnerships. He advises students on topics such as generative AI and optimization, though no student names are listed here.
