Amir R. Asadi

Leverhulme Early Career Fellow
Statistical Laboratory,
University of Cambridge

I am a Leverhulme Early Career Fellow at the Statistical Laboratory, part of the Department of Pure Mathematics and Mathematical Statistics at the University of Cambridge, a position I have held since September 2023. I am also a Fellow of the Isaac Newton Trust and a Postdoctoral Affiliate of Trinity College, Cambridge. From 2021 to 2023, I served as a Postdoctoral Research Associate at the same department. I earned my M.A. and Ph.D. in Electrical and Computer Engineering from Princeton University in 2017 and 2021, respectively, after completing dual B.Sc. degrees in Mathematics and Electrical Engineering from Sharif University of Technology in 2015. My research interests lie in machine learning, differential privacy, high-dimensional statistics, and information theory.

Download CV

Education

B.Sc. in Mathematics

B.Sc. in Electrical Engineering

September 2010 - August 2015

M.A. in Electrical and Computer Engineering

September 2015 - September 2017

Ph.D. in Electrical and Computer Engineering

September 2017 - July 2021

Awards and Honors

Leverhulme Early Career Fellowship from the Leverhulme Trust and the Isaac Newton Trust (2023-present)
Teaching Assistant Award from the Department of Electrical and Computer Engineering at Princeton University (2019)
Anthony Ephremides Fellowship from the Graduate School at Princeton University (2016)
Iranian Mathematical Olympiad Bronze Medal (2009)
Winner of the Tournament of Towns: International mathematical contest certified by the Russian Academy of Sciences (2009)
Membership of the Iranian National Elite Foundation (2009-present)

Publications

Gholamali Aminian, Amir R. Asadi, Idan Shenfeld & Youssef Mroueh. (2025) Theoretical Analysis of KL-regularized RLHF with Multiple Reference Models. arXiv preprint arXiv:2502.01203 [Link]
Gholamali Aminian, Amir R. Asadi, Tian Li, Ahmad Beirami, Gesine Reinert & Samuel N. Cohen. (2024) Generalization Error of the Tilted Empirical Risk. arXiv preprint arXiv:2409.19431 [Link]
Ankit Pensia, Amir R. Asadi, Varun Jog & Po-Ling Loh. (2024) Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints. IEEE Transactions on Information Theory
Amir R. Asadi. (2024) An Entropy-Based Model for Hierarchical Learning. Journal of Machine Learning Research, 25(187), pp. 1−45. [Link]
Amir R. Asadi & Po-Ling Loh. (2024) Entropic Regularization of Neural Networks: Self-Similar Approximations. Journal of Statistical Planning and Inference, 233, p.106181
Amir R. Asadi & Po-Ling Loh. (2023) On the Gibbs Exponential Mechanism and Private Data Generation. IEEE International Symposium on Information Theory (ISIT)
Ankit Pensia, Amir R. Asadi, Varun Jog & Po-Ling Loh. (2023) Simple Binary Hypothesis Testing under Local Differential Privacy and Communication Constraints. 2023 Conference on Learning Theory (COLT) (arXiv preprint arXiv:2301.03566). [Link]
Amir R. Asadi & Emmanuel Abbe. (2020) Maximum Multiscale Entropy and Neural Network Regularization. arXiv preprint arXiv:2006.14614. [Link]
Amir R. Asadi & Emmanuel Abbe. (2020) Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks. Journal of Machine Learning Research, 21(139), pp. 1-32. [Link]
Amir R. Asadi, Emmanuel Abbe, & Sergio Verdú. (2018) Chaining Mutual Information and Tightening Generalization Bounds. Advances in Neural Information Processing Systems (NeurIPS), pp. 7245-7254. [Link]
Amir R. Asadi, Emmanuel Abbe, & Sergio Verdú. (2017) Compressing Data on Graphs with Clusters. IEEE International Symposium on Information Theory (ISIT) pp. 1583-1587. [Link]
Majid Asadi, Amir R. Asadi. (2014) On the Failure Probability of Used Coherent Systems. Communications in Statistics, Theory and Methods, Vol. 43, pp. 2468-2475. [Link]
Amir R. Asadi. (2013) Problem 96.J with solution. The Mathematical Gazette, Vol. 97, No. 539, pp. 345-346, United Kingdom. [Link]

Ph.D. Dissertation

A. R. Asadi (2021) Neural Network Learning: A Multiscale-Entropy and Self-Similarity Approach. (Princeton University)

Google Scholar

Talks

Chennai Mathematical Institute, Chennai, India. January 2025
Department of Mathematical Sciences, Durham University, UK. May 2023
Department of Mathematics and Statistics, Lancaster University, UK. February 2023
Statistical Laboratory, University of Cambridge, UK. February 2023
Department of Computer Science, ETH Zürich, Switzerland. February 2021
NSF-Simons Collaboration on the Theoretical Foundations of Deep Learning. December 2020
Department of EECS, Massachusetts Institute of Technology, USA. December 2020
Center for Data Science, New York University, USA. June 2020
Laboratoire de Physique, École Normale Supérieure, France. May 2020
Department of Statistical Sciences, University of Toronto, Canada. April 2020
Department of Engineering, University of Cambridge, UK. March 2020
Institute for Advanced Study, Princeton, USA. October 2019 [YouTube Link]
Microsoft Research AI, Redmond, USA. September 2019

Workshop Organization

Co-organizer, 1st Cambridge Information Theory Colloquium, 21 April 2023
Co-organizer, 2nd Cambridge Information Theory Colloquium, 10 May 2024
Co-organizer, 8th London Symposium on Information Theory, which will take place on 14-16 May 2025

Personal

I enjoy staying active through exercise and watching sports, with a particular passion for football, Formula 1, and tennis. I also take pleasure in reading poetry, particularly works by Saadi and Hafez.