@misc{saxena2023sift, title={SIFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency}, author={Shreyas Saxena and Vithursan Thangarasa and Abhay Gupta and Sean Lie}, year={2023}, eprint={2303.11525}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2303.11525} }