@article{communicationefficient2dparallel, title = {Communication-Efficient, 2D Parallel Stochastic Gradient Descent for Distributed-Memory Optimization}, author = {Aditya Devarakonda and Ramakrishnan Kannan}, year = {2025}, eprint = {2501.07526}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.07526v1}, }