@misc{indiciae2e8285719538, title = {Towards Low-Overhead Resilience for Data Parallel Deep Learning}, author = {Nicolae, Bogdan and Hobson, Tanner and Yildiz, Orcun and Peterka, Thomas and Morozov, Dmitriy}, year = {2022}, doi = {10.1109/ccgrid54584.2022.00043}, url = {https://www.osti.gov/biblio/1887187}, note = {Source identifier: 1887187} }