Scholar
Ioannis (Yannis) Mitliagkas
Google Scholar ID: K757SxgAAAAJ
Associate Professor at Mila, University of Montréal
Citations & Impact
Citations
7,100
H-index
34
i10-index
47
Publications
20
Co-authors
75
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Canada CIFAR AI Chair; May 2024, paper 'No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths' accepted at ICML 2024; April 2024, second PhD student Reyhane Askari Hemmat successfully defended her thesis and continues as a research scientist at Meta, Montreal; June 2024, another PhD student Adam Ibrahim graduated and works as a research scientist at H, Paris.
Research Experience
- Currently an associate professor at the University of Montreal, core faculty member at Mila, staff research scientist at Google DeepMind, and affiliated researcher at Archimedes, Athens. He teaches ML to 100-200 grad students every fall and an advanced research class on deep learning theory every winter.
Education
- Before joining the University of Montreal, he was a postdoc with the Departments of Computer Science and Statistics at Stanford University and a PhD candidate at The University of Texas at Austin.
Background
- Researcher in machine learning. Academic, immigrant, amateur musician, runner. Research focuses on optimization, dynamics, and learning, with a focus on modern machine learning, especially at the intersection of systems and theory.
Miscellany
- Interests include music and running; co-founded and hosted the first two seasons of MTL MLOpt, a bi-weekly meeting of optimization experts; helped organize the Smooth games optimization and ML workshop series at NeurIPS; invited to participate in the Learning and Games semester at Simons Institute, Berkeley, CA, in spring 2022; honored to be invited to teach optimization for ML at the Neuromatch Academy's deep learning course for the last few summers.
