معرفی
Shahab Asoodeh is an Assistant Professor in the Department of Computing and Software at McMaster University since August 2021. He is also a Faculty Affiliate at the Vector Institute and collaborates with Meta's Statistics & Privacy Team. His research focuses on the interplay between information theory, machine learning, and privacy, addressing challenges in differential privacy, algorithmic fairness, and trustworthy AI.
Research interests include:
- Information-theoretic methods for privacy and fairness in machine learning
- Optimal noise design for differential privacy
- Contraction coefficients and data processing inequalities
- Sample complexity and hypothesis selection under privacy constraints
- Responsible AI with theoretical foundations
Recent publications highlight his work on differential privacy for sampling, fair classification, and information bottleneck bounds. His work often bridges theoretical insights (e.g., Rényi divergence, saddle-point accountants) with practical applications in machine learning and communications engineering.
Scientific awards:
- Natural Sciences and Engineering Research Council of Canada (NSERC): Discovery Grant and Launch Supplement (2022)
Contact: asoodehs@mcmaster.ca | asoodeh@mcmaster.ca
