My name is Tian Jin. Welcome to my homepage.

Bio and Interests

I am a 3rd year Ph.D. student at MIT advised by Michael Carbin and Jonathan Ragan-Kelley. I am interested in machine learning and programming systems.

Previously, I was a Research Engineer at IBM Thomas J. Watson Research Center. I was the technical lead for enabling deep neural network model inference on IBM mainframe machines. I also contributed to the compiler support for IBM Summit Supercomputer, which was the most powerful supercomputer in the world in 2018. I was supervised by Kevin O'Brien.

I graduated from Haverford College in 2017 with a dual degree in Computer Science and Mathematics, advised by David Wonnacott and Curtis Greene.


Our paper, "Pruning’s Effect on Generalization Through the Lens of Training and Regularization", has been accepted to NeurIPS 2022! Read the preprint on arXiv.

Brief Academic CV

Refereed Publications

Tian Jin, Michael Carbin, Daniel M. Roy, Jonathan Frankle, and Gintare Karolina Dziugaite. "Pruning’s Effect on Generalization Through the Lens of Training and Regularization." Conference on Neural Information Processing Systems (NeurIPS), 2022.

Luke Anderson, Andrew Adams, Karima Ma, Tzu-Mao Li, Tian Jin, Jonathan Ragan-Kelley. "Efficient Automatic Scheduling of Imaging and Vision Pipelines for the GPU." International Conference on Object-Oriented Programming Systems, Languages, and Applications (OOPSLA), 2021.

Tian Jin*, Zhun Liu*, Shengjia Yan, Alexandre Eichenberger, and Louis-Philippe Morency. "Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions." Annual Meeting of the Association for Computational Linguistics (ACL), 2020.

Tian Jin, Seokin Hong. "Split-CNN: Splitting Window-based Operations in Convolutional Neural Networks for Memory System Optimization." International Conference on Architectural Support for Programming Languages and Operating Systems (ASPOLOS), 2019.

Arpith Chacko Jacob, Alexandre E Eichenberger, Hyojin Sung, Samuel F Antao, Gheorghe-Teodor Bercea, Carlo Bertolli, Alexey Bataev, Tian Jin, Tong Chen, Zehra Sura, Georgios Rokos, and Kevin O'Brien. "Efficient Fork-Join on GPUs Through Warp Specialization." International Conference on High Performance Computing (HiPC), 2017.

Tian Jin, Nirmal Prajapati, Waruna Ranasinghe, Guillaume Iooss, Yun Zou, Sanjay Rajopadhye, and David G. Wonnacott. "Hybrid Static/Dynamic Schedules for Tiled Polyhedral Programs." arXiv Preprint, 2016.

David Wonnacott, Tian Jin, and Allison Lake"Automatic tiling of "mostly-tileable" loop nests." International Workshop on Polyhedral Compilation Techniques (IMPACT), 2015.


Guest lecturer in High-Performance Machine Learning. New York University, 2019, 2020.