Tianyun Zhang
About
Dr. Tianyun Zhang received his Ph.D. in electrical and computer engineering from Syracuse University in 2021. His research interests include model compression and hardware acceleration for artificial intelligence systems, adversarial machine learning and robust learning, and efficient machine learning. His research papers have been published in competitive conferences such as NeurIPS, ECCV, ICCV, AAAI, ICDM, ASPLOS, DAC, as well as high-impact journals such as IEEE Transactions on Neural Networks and Learning Systems (TNNLS) and Neurocomputing. Dr. Zhang employs many mathematical optimization techniques in 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 for robust learning over multiple domains. The ADMM-based weight pruning framework for deep neural networks, proposed in his work, is one of the state-of-the-art model compression methods.
Research Performance Summary
First Recorded Paper
A systematic DNN weight pruning framework using alternating direction method of multipliers
Year: 2018
Citations: 679
Venue: European Conference on Computer Vision 2018 (ECCV 2018)
Latest Recorded Paper
A min–max optimization framework for sparse multi-task deep neural network
Year: 2025
Citations: 0
Venue: Neurocomputing 650
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.