@article{cwyparametrizationforscalablelearningof, title = {CWY Parametrization: a Solution for Parallelized Optimization of Orthogonal and Stiefel Matrices}, author = {Valerii Likhosherstov and Jared Davis and Krzysztof Choromanski and Adrian Weller}, year = {2020}, eprint = {2004.08675}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2004.08675v3}, }