Home Research Publications CV

Mohsen Heidari

Assistant Professor

Department of Computer Science

Indiana University, Bloomington

mheidar@iu.edu Google Scholor

I am an Assistant Professor at the Department of Computer Science at Indiana University, Bloomington. I was a Visiting Assistant Professor at Purdue University. Before that, I was a Postdoctoral Research Associate at NSF Center for Science of Information (CSoI) based at Purdue University and hosted by Wojciech Szpankowski. I received my Ph.D. in Electrical Engineering (2019) and my M.Sc. in Applied Mathematics (2017) from the University of Michigan. I was fortunate to have Sandeep Pradhan as my advisor.

Research Interests

My research interests lie in theoretical machine learning, quantum computing and algorithms, and classical and quantum information theory.

My recent work has focused on adapting analytical tools (e.g., Fourier analysis) for developing and analyzing various learning methods both in classical and quantum frameworks.

For Prospective Students:

I am looking for Ph.D. students with a strong background in mathematics, algorithms, and quantum computing. If you are interested, please send me an Email with your CV.

Recent News

Sept. 22: Our paper Precise Regret Bounds for Log-loss via a Truncated Bayesian Algorithm got accepted in NeurIPS'22 and selected for oral presentation (~25.6% acceptance rate).
July 22: Thrilled to announce that our proposal about Learning From Classical and Quantum Data: a Fourier Perspective was funded by NSF.
May 22: New workshop on Quantum Algorithms, Information, and Learning was organized.
April 22: Our journal paper Sufficiently Informative and Relevant Features: An Information-Theoretic and Fourier-Based Characterization got accepted to IEEE Transactions on Information theory.
April 22: Two papers got accepted to ISIT'22:
- Sequential vs Fixed Design Regrets in Online Learning
- Upper Bounds on the Feedback Error Exponent of Channels With State and Memory
Feb. 22: Our paper Toward Physically Realizable Quantum Neural Networks was accepted and selected for oral presentation in AAAI'22 (~15% acceptance rate).

Oct 21: New paper Faithful Simulation of Distributed Quantum Measurements with Applications in Distributed Rate-Distortion Theory got accepted to IEEE Transactions on Information Theory.
May 21: New paper Finding Relevant Information via a Discrete Fourier Expansion got accepted to ICML'21.
Apr 21: New paper A Theoretical Framework for Learning from Quantum Data got accepted to ISIT'21.
Apr 21: New paper Information Sufficiency via Fourier Expansion got accepted to ISIT'21.
Apr 21: Gave a talk about Learning from Classical and Quantum data: A Fourier Perspective, at
- Purdue CS Theory Seminar
- University at Albany, SUNY
- Imperial College London