| Brief Bio: |
| Dr. Tianyun Zhang received his Ph.D. in electrical and computer engineering from Syracuse University in 2021. His research interests include model compression on deep neural networks, energy-efficient and high-performance implementations of deep learning and artificial intelligence systems, adversarial robustness on artificial intelligence systems, convex and non-convex optimization. His research papers have been published in competitive conferences such as ASPLOS, ECCV, ICDM, DAC, PAKDD, ACC, as well as journal IEEE Transactions on Neural Networks and Learning Systems (TNNLS).
Dr. Zhang employs many mathematical optimization techniques on the research of deep learning. He proposes to solve the weight pruning problem on deep neural networks using alternating direction method of multipliers (ADMM). He also proposes a unified min-max optimization framework on robust learning over multiple domains. The ADMM-based weight pruning framework for deep neural networks, proposed in his work, is one of state-of-the-art model compression method.
In his spare time, he likes many sports and exercises, such as basketball and hiking. |
|
