@inproceedings {280874, author = {Lianmin Zheng and Zhuohan Li and Hao Zhang and Yonghao Zhuang and Zhifeng Chen and Yanping Huang and Yida Wang and Yuanzhong Xu and Danyang Zhuo and Eric P. Xing and Joseph E. Gonzalez and Ion Stoica}, title = {Alpa: Automating Inter- and {Intra-Operator} Parallelism for Distributed Deep Learning}, booktitle = {16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)}, year = {2022}, isbn = {978-1-939133-28-1}, address = {Carlsbad, CA}, pages = {559--578}, url = {https://www.usenix.org/conference/osdi22/presentation/zheng-lianmin}, publisher = {USENIX Association}, month = jul } @inproceedings {273735, author = {Aurick Qiao and Sang Keun Choe and Suhas Jayaram Subramanya and Willie Neiswanger and Qirong Ho and Hao Zhang and Gregory R. Ganger and Eric P. Xing}, title = {Pollux: Co-adaptive Cluster Scheduling for Goodput-Optimized Deep Learning}, booktitle = {15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21)}, year = {2021}, isbn = {978-1-939133-22-9}, pages = {1--18}, url = {https://www.usenix.org/conference/osdi21/presentation/qiao}, publisher = {{USENIX} Association}, month = jul } @inproceedings {234924, author = {Jin Kyu Kim and Abutalib Aghayev and Garth A. Gibson and Eric P. Xing}, title = {{STRADS-AP}: Simplifying Distributed Machine Learning Programming without Introducing a New Programming Model}, booktitle = {2019 USENIX Annual Technical Conference (USENIX ATC 19)}, year = {2019}, isbn = {978-1-939133-03-8}, address = {Renton, WA}, pages = {207--222}, url = {https://www.usenix.org/conference/atc19/presentation/kim-jin}, publisher = {USENIX Association}, month = jul } @inproceedings {216069, author = {Shizhen Xu and Hao Zhang and Graham Neubig and Wei Dai and Jin Kyu Kim and Zhijie Deng and Qirong Ho and Guangwen Yang and Eric P. Xing}, title = {Cavs: An Efficient Runtime System for Dynamic Neural Networks}, booktitle = {2018 USENIX Annual Technical Conference (USENIX ATC 18)}, year = {2018}, isbn = {978-1-939133-01-4}, address = {Boston, MA}, pages = {937--950}, url = {https://www.usenix.org/conference/atc18/presentation/xu-shizen}, publisher = {USENIX Association}, month = jul } @inproceedings {216041, author = {Aurick Qiao and Abutalib Aghayev and Weiren Yu and Haoyang Chen and Qirong Ho and Garth A. Gibson and Eric P. Xing}, title = {Litz: Elastic Framework for {High-Performance} Distributed Machine Learning}, booktitle = {2018 USENIX Annual Technical Conference (USENIX ATC 18)}, year = {2018}, isbn = {978-1-939133-01-4}, address = {Boston, MA}, pages = {631--644}, url = {https://www.usenix.org/conference/atc18/presentation/qiao}, publisher = {USENIX Association}, month = jul } @inproceedings {203269, author = {Hao Zhang and Zeyu Zheng and Shizhen Xu and Wei Dai and Qirong Ho and Xiaodan Liang and Zhiting Hu and Jinliang Wei and Pengtao Xie and Eric P. Xing}, title = {Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on {GPU} Clusters}, booktitle = {2017 USENIX Annual Technical Conference (USENIX ATC 17)}, year = {2017}, isbn = {978-1-931971-38-6}, address = {Santa Clara, CA}, pages = {181--193}, url = {https://www.usenix.org/conference/atc17/technical-sessions/presentation/zhang}, publisher = {USENIX Association}, month = jul } @inproceedings {184014, author = {Henggang Cui and James Cipar and Qirong Ho and Jin Kyu Kim and Seunghak Lee and Abhimanu Kumar and Jinliang Wei and Wei Dai and Gregory R. Ganger and Phillip B. Gibbons and Garth A. Gibson and Eric P. Xing}, title = {Exploiting Bounded Staleness to Speed Up Big Data Analytics}, booktitle = {2014 USENIX Annual Technical Conference (USENIX ATC 14)}, year = {2014}, isbn = {978-1-931971-10-2}, address = {Philadelphia, PA}, pages = {37--48}, url = {https://www.usenix.org/conference/atc14/technical-sessions/presentation/cui}, publisher = {USENIX Association}, month = jun }