Amir Reza Asadi

Dr. Amir Reza Asadi is a Leverhulme Early Career Fellow at the Statistical Laboratory, part of the Department of Pure Mathematics and Mathematical Statistics at the University of Cambridge (since September 2023). He is also a Fellow of the Isaac Newton Trust and a Postdoctoral Affiliate of Trinity College, Cambridge. Previously, he held a Postdoctoral Research Associate position at the same department (2021–2023) and completed his Ph.D. and M.A. in Electrical and Computer Engineering at Princeton University (2017–2021), following dual B.Sc. degrees in Mathematics and Electrical Engineering from Sharif University of Technology (2010–2015).

His research focuses on machine learning, differential privacy, and information theory, with contributions to entropic regularization, generalization bounds, and privacy-preserving algorithms. His work bridges theoretical foundations and practical applications, such as neural network training and synthetic data generation.

• Education:
  • B.Sc. in Mathematics & Electrical Engineering, Sharif University of Technology (2010–2015)
  • M.A. in Electrical and Computer Engineering, Princeton University (2015–2017)
  • Ph.D. in Electrical and Computer Engineering, Princeton University (2017–2021)

His recent articles emphasize differential privacy in machine learning, entropy-based regularization techniques, and hierarchical learning models. He has organized workshops, including the 1st and 2nd Cambridge Information Theory Colloquia and the 8th London Symposium on Information Theory. His awards include the Leverhulme Early Career Fellowship, the Teaching Assistant Award from Princeton, and the Bronze Medal in the Iranian Mathematical Olympiad.

Amir actively collaborates with institutions worldwide, including MIT, NYU, ETH Zürich, and the Institute for Advanced Study. His work reflects a commitment to advancing theoretical frameworks while addressing real-world challenges in data privacy and algorithmic fairness.