Mohammad Mozaffari

PhD Student - Computer Department

University of Toronto

About Me

I am Mohammad Mozaffari, a third-year PhD student in the Computer Department at the University of Toronto supervised by Professor Maryam Mehri Dehnavi. I got my B.Sc. in Electrical Engineering with a minor degree in Computer Engineering from the University of Tehran.

My research interests broadly span machine learning, optimization, and sparsity. In particular, I'm interested in developing new algorithms that leverage sparsity in the training and inference of large-scale machine learning models. I am also interested in enhancing the distributed second-order optimization methods to improve the convergence rate of the training process.

Links

CV / LinkedIn / GitHub / Google Scholar

Email: Email

Mohammad Mozaffari

Publications

MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates.
M. Mozaffari, S. Li, Z. Zhang, and M. Mehri Dehnavi.
Accepted at Thirty-seventh Conference on Neural Information Processing Systems, NeurIPS, 2023.
MKOR GitHub - 

@inproceedings{
    mozaffari2023mkor,
    title={{MKOR}: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates},
    author={Mohammad Mozaffari and Sikan Li and Zhao Zhang and Maryam Mehri Dehnavi},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
    year={2023},
    url={https://openreview.net/forum?id=jcnvDO96N5}
}

Experience

Research Intern at Autodesk
Aug 2022 - December 2022
Manager: Massimiliano Meneghin
Accelerated a multi-GPU system (in CUDA) for scientific computing by profiling the code and detecting and utilizing possible fusion cases in the system.