Marina Meila

Professor, Cheriton School of Computer Science

Research interests: statistical learning; geometric/combinatorial data; unsupervised structure validation; dimension reduction; preference & explanation theory

Biography

Marina Meila is a Professor with the Cheriton School of Computer Science at the University of Waterloo, a Canada CIFAR Chair in AI with the Vector Institute, and an Affiliate Professor of Statistics at the University of Washington. Dr. Meila has made contributions to the foundations of unsupervised learning, focusing on tractable algorithms with guarantees of correctness. She is a former Program Chair of three of the four flagship Machine Learning conferences (AISTATS, UAI, ICML), and the General Chair of the upcoming ICML 2027 in Rio de Janeiro. Prof. Meila holds a MS degree in Automatic Control and Computer Science from the Polytechnic Institute of Bucharest, and a PhD from the Massachusetts Institute of Technology. Until 2025 she was Professor of Statistics at the University of Washington, Seattle.

Education

  • PhD, Massachusetts Institute of Technology
  • MSc, Automatic Control and Computer Science, Polytechnic Institute of Bucharest
Marina Meila

RESEARCH

Research Interests 

  • Statistical learning

  • Discovery of geometric and combinatorial structure in data

  • Validation of unsupervised structure learning (dimension reduction and dependency structure)

  • Development of rigorous algorithms for interpreting low-dimensional structures

  • Statistical analysis of preferences

  • Quantitative theory of explanation

PUBLICATIONS

Recent publications include:

  • Meilă, M., & Zhang, H. (2024). “Manifold Learning: What, How and Why”. Annual Reviews of Statistics and Its Application.
  • Meilă, M., & Chen, Y.-C. (2022). “Manifold Coordinates with Physical Meaning.” Journal of Machine Learning Research, 23(343), 1–68.
  • Meilă, M. (2017). “How to Tell When a Clustering Is (Approximately) Correct Using Convex Relaxations.” In Neural Information Processing Systems (NeurIPS).
  • Meilă, M. (2007). “Comparing clusterings—an information based distance”. Journal of multivariate analysis, 98(5), 873–895.
  • Meilă, M., & Shi, J. (2001). “A random walks view of spectral segmentation.” In International workshop on artificial intelligence and statistics (AISTATS).

CONTACT

Email : mmp@uwaterloo.ca